IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

DOCS operation support articles update (#17449)

Browse Source 
conformance table added
ARM merged with CPU
precision support and layout tables removed from the overview device article (info available in device articles)
This commit is contained in:
Karol Blaszczak 2023-05-31 12:01:55 +02:00 committed by GitHub
parent a757506f6f
commit a91446a875
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
22 changed files with 25436 additions and 1459 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/Extensibility_UG/Intro.md
View File

@ -23,10 +23,10 @@
openvino_docs_MO_DG_prepare_model_customize_model_optimizer_Customize_Model_Optimizer
The Intel® Distribution of OpenVINO™ toolkit supports neural network models trained with various frameworks, including
The Intel® Distribution of OpenVINO™ toolkit supports neural-network models trained with various frameworks, including
TensorFlow, PyTorch, ONNX, TensorFlow Lite, and PaddlePaddle (OpenVINO support for Apache MXNet, Caffe, and Kaldi is currently
being deprecated and will be removed entirely in the future). The list of supported operations is different for each of the supported frameworks.
To see the operations supported by your framework, refer to :doc:`Supported Framework Operations <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>`.
To see the operations supported by your framework, refer to :doc:`Supported Framework Operations <openvino_resources_supported_operations_frontend>`.
Custom operations, which are not included in the list, are not recognized by OpenVINO out-of-the-box. The need for custom operation may appear in two cases:

3
docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md
View File

@ -77,7 +77,8 @@ Q3. What does the message "[ ERROR ]: Unable to create ports for node with id" m
**A:** Most likely, Model Optimizer does not know how to infer output shapes of some layers in the given topology.
To lessen the scope, compile the list of layers that are custom for Model Optimizer: present in the topology,
absent in the :doc:`list of supported layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` for the target framework. Then, refer to available options in the corresponding section in the :doc:`[Legacy] Custom Layers in Model Optimizer <openvino_docs_MO_DG_prepare_model_customize_model_optimizer_Customize_Model_Optimizer>` page.
absent in the :doc:`list of supported operations <openvino_resources_supported_operations_frontend>` for the target framework.
Then, refer to available options in the corresponding section in the :doc:`[Legacy] Custom Layers in Model Optimizer <openvino_docs_MO_DG_prepare_model_customize_model_optimizer_Customize_Model_Optimizer>` page.
.. _question-7:

936
docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md
View File

@ -1,936 +0,0 @@
# Supported Framework Layers {#openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers}
@sphinxdirective
In this article, you can find lists of supported framework layers, grouped by frameworks.
Caffe Supported Layers
##########################################
========================================== ==========================================================================================
Layer Name in Caffe Limitations
========================================== ==========================================================================================
Axpy
BN
BatchNorm
Bias
Binarization (Intel experimental)
Concat
Convolution
ConvolutionBinary
Crop
Deconvolution
DetectionOutput
Dropout Not needed for inference.
Eltwise
Flatten
GlobalInput
InnerProduct
Input
LRN
Normalize
Python Supported only for the Python Proposal operation.
Permute
Pooling
Power
PReLU
PriorBox
PriorBoxClustered
Proposal
PSROIPooling
ROIPooling
RegionYolo
ReorgYolo
ReLU
Resample
Reshape
Scale
ShuffleChannel
Sigmoid
Slice
Softmax
Tile
========================================== ==========================================================================================
Apache MXNet Supported Symbols
##########################################
========================================== ==========================================================================================
Symbol Name in Apache MXNet Limitations
========================================== ==========================================================================================
_Plus
_contrib_arange_like
_contrib_box_nms
_contrib_DeformableConvolution
_contrib_DeformablePSROIPooling
_contrib_div_sqrt_dim
_contrib_MultiBoxDetection ``force_suppress`` = 1 is not supported, non-default variances are not supported.
_contrib_MultiBoxPrior
_contrib_Proposal
_copy Not needed for inference
_div_scalar
_greater_scalar
_minus_scalar
_mul_scalar
_plus_scalar
_random_uniform Operation provides sequence from uniform distribution, but exact values won't match.
_rnn_param_concat
_arange
_contrib_AdaptiveAvgPooling2D Converted to the Average Pooling with fixed paddings.
_maximum
_minimum
_np_roll
_zeros
add_n
arccosh
arcsinh
arctanh
batch_dot
broadcast_add
broadcast_div
broadcast_mul
broadcast_sub
BlockGrad
cumsum
div_scalar
elementwise_sub
elemwise_add
elemwise_mul
elemwise_sub
exp
expand_dims
greater_scalar
max
minus_scalar
null Not needed for inference.
LayerNorm ``output_mean_var`` = True is not supported.
repeat
rnn
rnn_param_concat
round
sigmoid
slice
SliceChannel
slice_axis
slice_channel
slice_like
softmax
stack
swapaxis
tile
transpose
zeros
Activation Supported ``act_type`` = ``relu``, ``sigmoid``, ``softrelu`` or ``tanh``
BatchNorm
Concat
Convolution
Crop ``center_crop`` = 1 is not supported.
Custom See :doc:`Custom Layers in Model Optimizer <openvino_docs_MO_DG_prepare_model_customize_model_optimizer_Customize_Model_Optimizer>`
Deconvolution
DeformableConvolution
DeformablePSROIPooling
Dropout Not needed for inference.
ElementWiseSum
Embedding
Flatten
FullyConnected
InstanceNorm
L2Normalization Only 4D input is supported.
LRN
LeakyReLU Supported ``act_type`` = ``prelu``, ``elu``, ``leaky``, ``gelu``
ones_like
Pad
Pooling
ROIPooling
ReLU
Reshape
ScaleShift
SoftmaxActivation
SoftmaxOutput
SoftSign
Take The attribute ``mode`` is not supported.
Tile
UpSampling
Where
zeros_like
========================================== ==========================================================================================
TensorFlow Supported Operations
#########################################
Some of TensorFlow operations do not match any OpenVINO operations. Yet, they are still supported by
Model Optimizer and can be used on constant propagation path. These layers are labeled
with ``Constant propagation`` in the table below:
========================================== ==========================================================================================
Operation Name in TensorFlow Limitations
========================================== ==========================================================================================
Abs
Acosh
Add
AddV2
AddN
All
Any
ArgMax
ArgMin
Asinh
Assert Not needed for inference.
Assign Not needed for inference.
AssignSub Not needed for inference.
Atanh
AvgPool
AvgPoolV2 Supported only for constant-foldable ``kernel_size`` and strides inputs.
AvgPool3D
BatchMatMul
BatchMatMulV2
BatchToSpaceND
BiasAdd
BlockLSTM
Bucketize CPU only.
BroadcastTo
Cast
Ceil
ClipByValue
Concat
ConcatV2
Const
Conv2D
Conv2DBackpropInput
Conv3D
Conv3DBackpropInputV2
Cos
Cosh
CropAndResize ``method`` = ``bilinear`` only.
CTCGreedyDecoder Supported only with decoded indices output in a dense format.
CTCLoss Supported only with decoded indices input in a dense format.
CumSum
DepthToSpace
DepthwiseConv2dNative
Einsum Supported only with equation that does not contain repeated labels within a subscript.
Elu
EmptyTensorList Supported only when it is part of a sub-graph of the special form.
Enter Supported only when it is fused to the TensorIterator layer.
Equal
Erf
Exit Supported only when it is fused to the TensorIterator layer.
Exp
ExpandDims
ExperimentalSparseWeightedSum CPU only.
ExtractImagePatches
EuclideanNorm
FakeQuantWithMinMaxVars
FakeQuantWithMinMaxVarsPerChannel
FFT Supported only when it is part of a sub-graph of the special form.
FFT2D Supported only when it is part of a sub-graph of the special form.
FFT3D Supported only when it is part of a sub-graph of the special form.
FIFOQueueV2 Supported only when it is part of a sub-graph of the special form.
Fill
Floor
FloorDiv
FloorMod
FusedBatchNorm
FusedBatchNormV2
FusedBatchNormV3
Gather
GatherNd
GatherTree
GatherV2
Greater
GreaterEqual
Identity Not needed for shape inference.
IdentityN
IFFT Supported only when it is part of a sub-graph of the special form.
IFFT2D Supported only when it is part of a sub-graph of the special form.
IFFT3D Supported only when it is part of a sub-graph of the special form.
IteratorGetNext Supported only when it is part of a sub-graph of the special form.
LRN
LeakyRelu
Less
LessEqual
Log
Log1p
LogicalAnd
LogicalOr
LogicalNot
LogSoftmax
LookupTableInsertV2 Supported only when it is part of a sub-graph of the special form.
LoopCond Supported only when it is fused to the TensorIterator layer.
MatMul
Max
MaxPool
MaxPoolV2 Supported only for constant-foldable ``kernel_size`` and strides inputs.
MaxPool3D
Maximum
Mean
Merge Supported only when it is fused to the TensorIterator layer.
Min
Minimum
MirrorPad
Mod
Mul
Neg
NextIteration Supported only when it is fused to the TensorIterator layer.
NonMaxSuppressionV2
NonMaxSuppressionV3
NonMaxSuppressionV4
NonMaxSuppressionV5
NotEqual
NoOp
OneHot
Pack
Pad
PadV2
Placeholder
PlaceholderWithDefault
Prod
QueueDequeue Supported only when it is part of a sub-graph of the special form.
QueueDequeueUpToV2 Supported only when it is part of a sub-graph of the special form.
QueueDequeueV2 Supported only when it is part of a sub-graph of the special form.
RandomUniform
RandomUniformInt
Range
Rank
RealDiv
Reciprocal
Relu
Relu6
Reshape
ResizeBilinear
ResizeNearestNeighbor
ResourceGather
ReverseSequence
ReverseV2 Supported only when it can be converted to the ReverseSequence operation.
Roll
Round
Pow
Rsqrt
ScatterNd
Select
SelectV2
Shape
Sigmoid
Sin
Sinh
Size
Slice
Softmax
Softplus
Softsign
SpaceToBatchND
SpaceToDepth
SparseFillEmptyRows Supported only when it is part of a sub-graph of the special form.
SparseReshape Supported only when it is part of a sub-graph of the special form.
SparseSegmentSum Supported only when it is part of a sub-graph of the special form.
SparseSegmentMean Supported only when it is part of a sub-graph of the special form.
SparseToDense CPU only
Split
SplitV
Sqrt
Square
SquaredDifference
Square
Squeeze Cases in which squeeze axis is not specified are not supported.
StatelessWhile
StopGradient Not needed for shape inference.
StridedSlice Supported only for constant-foldable ``begin``, ``end``, and ``strides`` inputs.
Sub
Sum
Swish
swish_f32
Switch Control flow propagation.
Tan
Tanh
TensorArrayGatherV3 Supported only when it is fused to the TensorIterator layer.
TensorArrayReadV3 Supported only when it is fused to the TensorIterator layer.
TensorArrayScatterV3 Supported only when it is fused to the TensorIterator layer.
TensorArraySizeV3 Supported only when it is fused to the TensorIterator layer.
TensorArrayV3 Supported only when it is fused to the TensorIterator layer.
TensorArrayWriteV3 Supported only when it is fused to the TensorIterator layer.
TensorListPushBack Supported only when it is part of a sub-graph of the special form.
Tile
TopkV2
Transpose
Unpack
Variable
VariableV2
Where Supported only when it is part of a sub-graph of the special form.
ZerosLike
========================================== ==========================================================================================
TensorFlow 2 Keras Supported Operations
##########################################
========================================== ==========================================================================================
Operation Name in TensorFlow 2 Keras Limitations
========================================== ==========================================================================================
ActivityRegularization
Add
AdditiveAttention
AlphaDropout
Attention
Average
AveragePooling1D
AveragePooling2D
AveragePooling3D
BatchNormalization
Bidirectional
Concatenate
Conv1D
Conv1DTranspose Not supported if ``dilation`` is not equal to 1.
Conv2D
Conv2DTranspose
Conv3D
Conv3DTranspose
Cropping1D
Cropping2D
Cropping3D
Dense
DenseFeatures Not supported for categorical and crossed features.
DepthwiseConv2D
Dot
Dropout
ELU
Embedding
Flatten
GRU
GRUCell
GaussianDropout
GaussianNoise
GlobalAveragePooling1D
GlobalAveragePooling2D
GlobalAveragePooling3D
GlobalMaxPool1D
GlobalMaxPool2D
GlobalMaxPool3D
LSTM
LSTMCell
Lambda
LayerNormalization
LeakyReLU
LocallyConnected1D
LocallyConnected2D
MaxPool1D
MaxPool2D
MaxPool3D
Maximum
Minimum
Multiply
PReLU
Permute
RNN Not supported for some custom cells.
ReLU
RepeatVector
Reshape
Roll
SeparableConv1D
SeparableConv2D
SimpleRNN
SimpleRNNCell
Softmax
SpatialDropout1D
SpatialDropout2D
SpatialDropout3D
StackedRNNCells
Subtract
ThresholdedReLU
TimeDistributed
UpSampling1D
UpSampling2D
UpSampling3D
ZeroPadding1D
ZeroPadding2D
ZeroPadding3D
========================================== ==========================================================================================
Kaldi Supported Layers
##########################################
========================================== ==========================================================================================
Symbol Name in Kaldi Limitations
========================================== ==========================================================================================
addshift
affinecomponent
affinecomponentpreconditionedonline
affinetransform
backproptruncationcomponent
batchnormcomponent
clipgradientcomponent Not needed for inference.
concat
convolutional1dcomponent
convolutionalcomponent
copy
dropoutmaskcomponent
elementwiseproductcomponent
fixedaffinecomponent
fixedbiascomponent
fixedscalecomponent
generaldropoutcomponent Not needed for inference.
linearcomponent
logsoftmaxcomponent
lstmnonlinearitycomponent
lstmprojected
lstmprojectedstreams
maxpoolingcomponent
naturalgradientaffinecomponent
naturalgradientperelementscalecomponent
noopcomponent Not needed for inference.
normalizecomponent
parallelcomponent
pnormcomponent
rectifiedlinearcomponent
rescale
sigmoid
sigmoidcomponent
softmax
softmaxComponent
specaugmenttimemaskcomponent Not needed for inference.
splicecomponent
tanhcomponent
tdnncomponent
timeheightconvolutioncomponent
========================================== ==========================================================================================
ONNX Supported Operators
##########################################
Standard ONNX Operators
++++++++++++++++++++++++++++++++++++++++++
========================================== ==========================================================================================
ONNX Operator Name
========================================== ==========================================================================================
Abs
Acos
Acosh
And
ArgMin
ArgMax
Asin
Asinh
Atan
ATen
Atanh
AveragePool
BatchNormalization
BitShift
Cast
CastLike
Ceil
Clip
Concat
Constant
ConstantOfShape
Conv
ConvInteger
ConvTranspose
Compress
Cos
Cosh
ConstantFill
CumSum
DepthToSpace
DequantizeLinear
Div
Dropout
Einsum
Elu
Equal
Erf
Exp
Expand
EyeLike
Flatten
Floor
Gather
GatherElements
GatherND
Gemm
GlobalAveragePool
GlobalLpPool
GlobalMaxPool
Greater
GRU
Hardmax
HardSigmoid
HardSwish
Identity
If
ImageScaler
InstanceNormalization
LeakyRelu
Less
Log
LogSoftmax
Loop
LpNormalization
LRN
LSTM
MatMulInteger
MatMul
MaxPool
Max
Mean
MeanVarianceNormalization
Min
Mod
Mul
Neg
NonMaxSuppression
NonZero
Not
Or
OneHot
Pad
Pow
PRelu
QLinearConv
QLinearMatMul
QuantizeLinear
Range
RandomNormal
RandomNormalLike
RandomUniform
RandomUniformLike
Reciprocal
ReduceLogSum
ReduceLogSumExp
ReduceL1
ReduceL2
ReduceMax
ReduceMean
ReduceMin
ReduceProd
ReduceSum
ReduceSumSquare
Relu
Reshape
Resize
ReverseSequence
RNN
RoiAlign
Round
ScatterElements
ScatterND
Selu
Shape
Shrink
Sigmoid
Sign
Sin
Sinh
Size
Slice
Softmax
Softplus
Softsign
SpaceToDepth
Split
Sqrt
Squeeze
Sub
Sum
Tan
Tanh
ThresholdedRelu
Tile
TopK
Transpose
Unsqueeze
Where
Xor
========================================== ==========================================================================================
Deprecated ONNX Operators (Supported)
++++++++++++++++++++++++++++++++++++++++++
========================================== ==========================================================================================
ONNX Operator Name
========================================== ==========================================================================================
Affine
Crop
Scatter
Upsample
========================================== ==========================================================================================
Operators From the org.openvinotoolkit Domain
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
===================================================== ===============================================================================
Custom ONNX Operator Name
===================================================== ===============================================================================
DeformableConv2D
DetectionOutput
ExperimentalDetectronDetectionOutput
ExperimentalDetectronGenerateProposalsSingleImage
ExperimentalDetectronGroupNorm
ExperimentalDetectronPriorGridGenerator
ExperimentalDetectronROIFeatureExtractor
ExperimentalDetectronTopKROIs
FakeQuantize
GroupNorm
Normalize
PriorBox
PriorBoxClustered
Swish
===================================================== ===============================================================================
Operators From the com.microsoft Domain
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
===================================================== ===============================================================================
Custom ONNX Operator Name
===================================================== ===============================================================================
Attention
BiasGelu
EmbedLayerNormalization
SkipLayerNormalization
===================================================== ===============================================================================
PaddlePaddle Supported Operators
###########################################################
paddlepaddle >= 2.1
========================================== ===============================================================================
Operator Name in PaddlePaddle Limitations
========================================== ===============================================================================
arg_max The ``int32`` output data_type is not supported.
adaptive_pool2d The ``NHWC`` data_layout is not supported.
assign
assign_value
batch_norm
bicubic_interp
bilinear_interp ``NCW``, ``NWC``, ``NHWC``, ``NCDHW``, ``NDHWC`` data_layout are not supported
bmm
box_coder
cast
ceil
clip
concat
conditional_block
conv2d ``NHWC`` data_layout is not supported
conv2d_transpose
cumsum
deformable_conv
depthwise_conv2d ``NHWC`` data_layout is not supported.
depthwise_conv2d_transpose
dropout
elementwise_add
elementwise_div
elementwise_floordiv
elementwise_max
elementwise_min
elementwise_mod
elementwise_mul
elementwise_pow
elementwise_sub
equal
exp
expand
fill_any_like
fill_constant
fill_constant_batch_size_like
flatten_contiguous_range
floor
gather
gather_nd
gelu
generate_proposals
greater_equal
greater_than
group_norm
hard_sigmoid
hard_swish
index_select
layer_norm
leaky_relu
less_than
linear_interp
log
logical_and
logical_not
logical_or
logical_xor
lookup_table
matmul
matrix_nms Only supports IE CPU plugin with "number of selected boxes" static shape (e.g.: ``min(min(num_boxes, nms_top_k) * num_classes_output, keep_top_k)``).
max_pool2d_with_index
meshgrid
multiclass_nms Only supports IE CPU plugin with "number of selected boxes" static shape (e.g.: ``min(min(num_boxes, nms_top_k) * num_classes_output, keep_top_k)``).
nearest_interp ``NCW``, ``NWC``, ``NHWC``, ``NCDHW``, ``NDHWC`` data_layout are not supported.
not_equal
one_hot_v2
p_norm
pad3d ``Circular`` mode is not supported.
pool2d ``NHWC`` data_layout is not supported.
pow
prior_box
range
reduce_max
reduce_mean
reduce_min
reduce_prod
reduce_sum
relu
reshape
reverse
rnn ``SimpleRNN`` and ``GRU`` modes are not supported.
roi_align
scale
select_input
shape
sigmoid
slice
softmax
softplus
softshrink
split
sqrt
squeeze
stack
strided_slice
sum
swish
sync_batch_norm
tanh
tile
top_k
transpose
trilinear_interp
unsqueeze
where
where_index
while
yolo_box
========================================== ===============================================================================
TensorFlow Lite Supported Operators
###########################################################
========================================== ===============================================================================
Operator Name in TensorFlow Lite Limitations
========================================== ===============================================================================
ABS
ADD
ADD_N
ARG_MAX
ARG_MIN
AVERAGE_POOL_2D
BATCH_MATMUL
BATCH_TO_SPACE_ND
BROADCAST_ARGS
BROADCAST_TO
CAST
CEIL
COMPLEX_ABS Supported in a specific pattern with RFFT2D
CONCATENATION
CONV_2D
COS
DEPTH_TO_SPACE
DEPTHWISE_CONV_2D
DEQUANTIZE
DIV
ELU
EQUAL
EXP
EXPAND_DIMS
FILL
FLOOR
FLOOR_DIV
FLOOR_MOD
FULLY_CONNECTED
GATHER
GATHER_ND
GREATER
GREATER_EQUAL
HARD_SWISH
L2_NORMALIZATION
LEAKY_RELU
LESS
LESS_EQUAL
LOG
LOG_SOFTMAX
LOGICAL_AND
LOGICAL_NOT
LOGICAL_OR
LOGISTIC
MATRIX_DIAG
MAX_POOL_2D
MAXIMUM
MEAN
MINIMUM
MIRROR_PAD
MUL
NEG
NOT_EQUAL
ONE_HOT
PACK
PAD
PADV2
POW
PRELU
QUANTIZE
RANGE
RANK
REDUCE_ALL
REDUCE_ANY
REDUCE_MAX
REDUCE_MIN
REDUCE_PROD
RELU
RELU6
RESHAPE
RESIZE_BILINEAR
RESIZE_NEAREST_NEIGHBOR
REVERSE_V2
RFFT2D Supported in a specific pattern with COMPLEX_ABS
ROUND
RSQRT
SCATTER_ND
SEGMENT_SUM
SELECT
SELECT_V2
SHAPE
SIGN
SIN
SLICE
SOFTMAX
SPACE_TO_BATCH_ND
SPACE_TO_DEPTH
SPLIT
SPLIT_V
SQRT
SQUARE
SQUARED_DIFFERENCE
SQUEEZE
STRIDED_SLICE
SUB
SUM
TANH
TILE
TOPK_V2
TRANSPOSE
TRANSPOSE_CONV
UNIQUE
UNPACK
WHERE
ZEROS_LIKE
========================================== ===============================================================================
@endsphinxdirective

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md
View File

@ -91,7 +91,7 @@ Internally, when you run Model Optimizer, it loads the model, goes through the t
Supported Caffe Layers
#######################
For the list of supported standard layers, refer to the :doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` page.
For the list of supported standard layers, refer to the :doc:`Supported Operations <openvino_resources_supported_operations_frontend>` page.
Frequently Asked Questions (FAQ)
################################

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md
View File

@ -77,7 +77,7 @@ The Model Optimizer finds the last layer of the topology and removes this layer
Supported Kaldi Layers
######################
For the list of supported standard layers, refer to the :doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` page.
For the list of supported standard layers, refer to the :doc:`Supported Operations <openvino_resources_supported_operations_frontend>` page.
Additional Resources
####################

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md
View File

@ -51,7 +51,7 @@ Internally, when you run Model Optimizer, it loads the model, goes through the t
Supported MXNet Layers
#######################
For the list of supported standard layers, refer to the :doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` page.
For the list of supported standard layers, refer to the :doc:`Supported Operations <openvino_resources_supported_operations>` page.
Frequently Asked Questions (FAQ)
################################

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_ONNX.md
View File

@ -25,7 +25,7 @@ There are no ONNX specific parameters, so only framework-agnostic parameters are
Supported ONNX Layers
#####################
For the list of supported standard layers, refer to the :doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` page.
For the list of supported standard layers, refer to the :doc:`Supported Operations <openvino_resources_supported_operations_frontend>` page.
Additional Resources
####################

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md
View File

@ -102,7 +102,7 @@ Converting certain PaddlePaddle models may require setting ``example_input`` or
Supported PaddlePaddle Layers
#############################
For the list of supported standard layers, refer to the :doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` page.
For the list of supported standard layers, refer to the :doc:`Supported Operations <openvino_resources_supported_operations_frontend>` page.
Officially Supported PaddlePaddle Models
########################################

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md
View File

@ -283,7 +283,7 @@ MO Python API supports passing TensorFlow/TensorFlow2 models directly from memor
Supported TensorFlow and TensorFlow 2 Keras Layers
##################################################
For the list of supported standard layers, refer to the :doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` page.
For the list of supported standard layers, refer to the :doc:`Supported Operations <openvino_resources_supported_operations_frontend>` page.
Frequently Asked Questions (FAQ)
################################

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow_Lite.md
View File

@ -13,7 +13,7 @@ To convert a TensorFlow Lite model, use the ``mo`` script and specify the path t
Supported TensorFlow Lite Layers
###################################
For the list of supported standard layers, refer to the :doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` page.
For the list of supported standard layers, refer to the :doc:`Supported Operations <openvino_resources_supported_operations_frontend>` page.
Supported TensorFlow Lite Models
###################################

7
docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md
View File

@ -17,16 +17,9 @@ OpenVINO™ Runtime can infer deep learning models using the following device ty
* :doc:`CPU <openvino_docs_OV_UG_supported_plugins_CPU>`
* :doc:`GPU <openvino_docs_OV_UG_supported_plugins_GPU>`
* :doc:`GNA <openvino_docs_OV_UG_supported_plugins_GNA>`
* :doc:`Arm® CPU <openvino_docs_OV_UG_supported_plugins_CPU>`
For a more detailed list of hardware, see :doc:`Supported Devices <openvino_docs_OV_UG_supported_plugins_Supported_Devices>`.
Devices similar to the ones used for benchmarking can be accessed, using `Intel® DevCloud for the Edge <https://devcloud.intel.com/edge/>`__,
a remote development environment with access to Intel® hardware and the latest versions of the Intel® Distribution of the OpenVINO™ Toolkit.
`Learn more <https://devcloud.intel.com/edge/get_started/devcloud/>`__ or `Register here <https://inteliot.force.com/DevcloudForEdge/s/>`__.
.. _devicesupport-feature-support-matrix:

503
docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md
View File

@ -1,503 +0,0 @@
# Supported Devices {#openvino_docs_OV_UG_supported_plugins_Supported_Devices}
@sphinxdirective
The OpenVINO runtime can infer various models of different input and output formats. Here, you can find configurations
supported by OpenVINO devices, which are CPU, GPU, or GNA (Gaussian neural accelerator coprocessor). Currently, 11th generation and later processors (currently up to 13th generation) provide a further performance boost, especially with INT8 models.
.. note::
With OpenVINO™ 2023.0 release, support has been cancelled for all VPU accelerators based on Intel® Movidius™.
The OpenVINO Runtime provides unique capabilities to infer deep learning models on the following devices:
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
| OpenVINO Device | Supported Hardware |
+==========================================================================+===============================================================================================================+
|| :doc:`GPU <openvino_docs_OV_UG_supported_plugins_GPU>` | Intel® Processor Graphics, including Intel® HD Graphics and Intel® Iris® Graphics |
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
|| :doc:`CPU (x86) <openvino_docs_OV_UG_supported_plugins_CPU>` | Intel® Xeon® with Intel® Advanced Vector Extensions 2 (Intel® AVX2), Intel® Advanced Vector |
|| | Extensions 512 (Intel® AVX-512), Intel® Advanced Matrix Extensions (Intel® AMX), |
|| | Intel® Core™ Processors with Intel® AVX2, |
|| | Intel® Atom® Processors with Intel® Streaming SIMD Extensions (Intel® SSE) |
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
|| :doc:`CPU (Arm®) <openvino_docs_OV_UG_supported_plugins_CPU>` | Raspberry Pi™ 4 Model B, Apple® Mac with Apple silicon |
|| | |
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
|| :doc:`GNA plugin <openvino_docs_OV_UG_supported_plugins_GNA>` | Intel® Speech Enabling Developer Kit, Amazon Alexa* Premium Far-Field Developer Kit, Intel® |
|| (available in the Intel® Distribution of OpenVINO™ toolkit) | Pentium® Silver J5005 Processor, Intel® Pentium® Silver N5000 Processor, Intel® |
|| | Celeron® J4005 Processor, Intel® Celeron® J4105 Processor, Intel® Celeron® |
|| | Processor N4100, Intel® Celeron® Processor N4000, Intel® Core™ i3-8121U Processor, |
|| | Intel® Core™ i7-1065G7 Processor, Intel® Core™ i7-1060G7 Processor, Intel® |
|| | Core™ i5-1035G4 Processor, Intel® Core™ i5-1035G7 Processor, Intel® Core™ |
|| | i5-1035G1 Processor, Intel® Core™ i5-1030G7 Processor, Intel® Core™ i5-1030G4 Processor, |
|| | Intel® Core™ i3-1005G1 Processor, Intel® Core™ i3-1000G1 Processor, |
|| | Intel® Core™ i3-1000G4 Processor |
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
|| :doc:`Multi-Device <openvino_docs_OV_UG_Running_on_multiple_devices>` | Multi-Device execution enables simultaneous inference of the same model on several devices in parallel |
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
|| :doc:`Auto-Device plugin <openvino_docs_OV_UG_supported_plugins_AUTO>` | Auto-Device enables selecting devices for inference automatically |
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
|| :doc:`Heterogeneous plugin <openvino_docs_OV_UG_Hetero_execution>` | Heterogeneous execution enables automatically splitting inference between several devices (for example if |
|| | a device doesn't support certain operations) |
+--------------------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------+
.. note::
ARM® CPU plugin is a community-level add-on to OpenVINO™. Intel® welcomes community participation in the OpenVINO™
ecosystem, technical questions and code contributions on community forums. However, this component has not
undergone full release validation or qualification from Intel®, hence no official support is offered.
Devices similar to the ones we have used for benchmarking can be accessed using `Intel® DevCloud for the Edge <https://devcloud.intel.com/edge/>`__,
a remote development environment with access to Intel® hardware and the latest versions of the Intel® Distribution
of OpenVINO™ Toolkit. `Learn more <https://devcloud.intel.com/edge/get_started/devcloud/>`__ or `Register here <https://inteliot.force.com/DevcloudForEdge/s/>`__.
Supported Configurations
###########################################################
The OpenVINO Runtime can inference models in different formats with various input and output formats.
This page shows supported and optimal configurations for each plugin.
Terminology
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+------------------+----------------------------------------------+
| Acronym/Term | Description |
+==================+==============================================+
| FP32 format | Single-precision floating-point format |
+------------------+----------------------------------------------+
| BF16 format | Brain floating-point format |
+------------------+----------------------------------------------+
| FP16 format | Half-precision floating-point format |
+------------------+----------------------------------------------+
| I16 format | 2-byte signed integer format |
+------------------+----------------------------------------------+
| I8 format | 1-byte signed integer format |
+------------------+----------------------------------------------+
| U16 format | 2-byte unsigned integer format |
+------------------+----------------------------------------------+
| U8 format | 1-byte unsigned integer format |
+------------------+----------------------------------------------+
NHWC, NCHW, and NCDHW refer to the data ordering in batches of images:
* NHWC and NCHW refer to image data layout.
* NCDHW refers to image sequence data layout.
Abbreviations in the support tables are as follows:
* N: Number of images in a batch
* D: Depth. Depend on model it could be spatial or time dimension
* H: Number of pixels in the vertical dimension
* W: Number of pixels in the horizontal dimension
* C: Number of channels
CHW, NC, C - Tensor memory layout.
For example, the CHW value at index (c,h,w) is physically located at index (c\*H+h)\*W+w, for others by analogy.
Supported Model Formats
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+------------------+--------------------------+--------------------------+------------------------+
| Plugin | FP32 | FP16 | I8 |
+==================+==========================+==========================+========================+
| CPU plugin | Supported and preferred | Supported | Supported |
+------------------+--------------------------+--------------------------+------------------------+
| GPU plugin | Supported | Supported and preferred | Supported |
+------------------+--------------------------+--------------------------+------------------------+
| GNA plugin | Supported | Supported | Not supported |
+------------------+--------------------------+--------------------------+------------------------+
| Arm® CPU plugin | Supported and preferred | Supported | Supported (partially) |
+------------------+--------------------------+--------------------------+------------------------+
For :doc:`Multi-Device <openvino_docs_OV_UG_Running_on_multiple_devices>` and
:doc:`Heterogeneous <openvino_docs_OV_UG_Hetero_execution>` executions, the supported models formats depends
on the actual underlying devices.
Supported Input Precision
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+------------------+------------+----------------+--------------+----------------+----------------+----------------+
| Plugin | FP32 | FP16 | U8 | U16 | I8 | I16 |
+==================+============+================+==============+================+================+================+
| CPU plugin | Supported | Supported | Supported | Supported | Supported | Supported |
+------------------+------------+----------------+--------------+----------------+----------------+----------------+
| GPU plugin | Supported | Supported\* | Supported\* | Supported\* | Not supported | Supported\* |
+------------------+------------+----------------+--------------+----------------+----------------+----------------+
| GNA plugin | Supported | Not supported | Supported | Not supported | Supported | Supported |
+------------------+------------+----------------+--------------+----------------+----------------+----------------+
| Arm® CPU plugin | Supported | Supported | Supported | Supported | Not supported | Not supported |
+------------------+------------+----------------+--------------+----------------+----------------+----------------+
\* - Supported via ``SetBlob`` only, ``GetBlob`` returns FP32
For :doc:`Multi-Device <openvino_docs_OV_UG_Running_on_multiple_devices>` and
:doc:`Heterogeneous <openvino_docs_OV_UG_Hetero_execution>` executions, the supported input precision
depends on the actual underlying devices. *Generally, U8 is preferable as it is most ubiquitous*.
Supported Output Precision
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+------------------+-----------------------------+
| Plugin | FP32 | FP16 |
+==================+============+================+
| CPU plugin | Supported | Supported |
+------------------+------------+----------------+
| GPU plugin | Supported | Supported |
+------------------+------------+----------------+
| GNA plugin | Supported | Not supported |
+------------------+------------+----------------+
| Arm® CPU plugin | Supported | Supported |
+------------------+------------+----------------+
For :doc:`Multi-Device <openvino_docs_OV_UG_Running_on_multiple_devices>` and
:doc:`Heterogeneous <openvino_docs_OV_UG_Hetero_execution>` executions, the supported output precision
depends on the actual underlying devices. *Generally, FP32 is preferable as it is most ubiquitous*.
Supported Input Layout
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+------------------+----------------+------------+------------+------------+
| Plugin | NCDHW | NCHW | NHWC | NC |
+==================+================+============+============+============+
| CPU plugin | Supported | Supported | Supported | Supported |
+------------------+----------------+------------+------------+------------+
| GPU plugin | Supported | Supported | Supported | Supported |
+------------------+----------------+------------+------------+------------+
| GNA plugin | Not supported | Supported | Supported | Supported |
+------------------+----------------+------------+------------+------------+
| Arm® CPU plugin | Not supported | Supported | Supported | Supported |
+------------------+----------------+------------+------------+------------+
Supported Output Layout
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+-----------------------+--------+-------+------+-----+----+
| Number of dimensions | 5 | 4 | 3 | 2 | 1 |
+=======================+========+=======+======+=====+====+
| Layout | NCDHW | NCHW | CHW | NC | C |
+-----------------------+--------+-------+------+-----+----+
For setting relevant configuration, refer to the
:doc:`Integrate with Customer Application <openvino_docs_OV_UG_Integrate_OV_with_your_application>`
topic (step 3 "Configure input and output").
Supported Layers
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
The following layers are supported by the plugins:
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Layers | GPU | CPU | GNA | Arm® CPU |
+================================+================+=================+================+====================+
| Abs | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Acos | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Acosh | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-Clamp | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-ELU | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-Exp | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-Leaky ReLU | Supported | Supported\*\*\* | Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-Not | Supported | Supported\*\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-PReLU | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-ReLU | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-ReLU6 | Supported | Supported\*\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-Sigmoid/Logistic | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Activation-TanH | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ArgMax | Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Asin | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Asinh | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Atan | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Atanh | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| BatchNormalization | Supported | Supported | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| BinaryConvolution | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Broadcast | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Ceil | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Concat | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Const | Supported | Supported | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Convolution-Dilated | Supported | Supported | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Convolution-Dilated 3D | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Convolution-Grouped | Supported | Supported | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Convolution-Grouped 3D | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Convolution-Ordinary | Supported | Supported | Supported\* | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Convolution-Ordinary 3D | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Cos | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Cosh | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Crop | Supported | Supported | Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| CTCGreedyDecoder | Supported\*\* | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Deconvolution | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Deconvolution 3D | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| DeformableConvolution | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| DepthToSpace | Supported | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| DetectionOutput | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-And | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Add | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Div | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Equal | Supported | Supported\*\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-FloorMod | Supported | Supported\*\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Greater | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-GreaterEqual | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Less | Supported | Supported\*\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-LessEqual | Supported | Supported\*\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-LogicalAnd | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-LogicalOr | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-LogicalXor | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Max | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Min | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Mul | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-NotEqual | Supported | Supported\*\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Pow | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Prod | Supported | Supported\*\*\* | Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-SquaredDiff | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Sub | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Eltwise-Sum | Supported | Supported\*\*\* | Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Erf | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Exp | Supported | Supported | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| FakeQuantize | Not Supported | Supported | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Fill | Not Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Flatten | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Floor | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| FullyConnected (Inner Product) | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Gather | Supported | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| GatherTree | Not Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Gemm | Supported | Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| GRN | Supported\*\* | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| HardSigmoid | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Interp | Supported\*\* | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Log | Supported | Supported\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| LRN (Norm) | Supported | Supported | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| LSTMCell | Supported | Supported | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| GRUCell | Supported | Supported | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| RNNCell | Supported | Supported | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| LSTMSequence | Supported | Supported | Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| GRUSequence | Supported | Supported | Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| RNNSequence | Supported | Supported | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| LogSoftmax | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Memory | Not Supported | Supported | Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| MVN | Supported | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Neg | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| NonMaxSuppression | Not Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Normalize | Supported | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| OneHot | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Pad | Supported | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Permute | Supported | Supported | Supported\* | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Pooling(AVG,MAX) | Supported | Supported | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Pooling(AVG,MAX) 3D | Supported | Supported | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Power | Supported | Supported\*\* | Supported\* | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| PowerFile | Not Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| PriorBox | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| PriorBoxClustered | Supported\*\* | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Proposal | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| PSROIPooling | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Range | Not Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Reciprocal | Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceAnd | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceL1 | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceL2 | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceLogSum | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceLogSumExp | Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceMax | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceMean | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceMin | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceOr | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceProd | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceSum | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReduceSumSquare | Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| RegionYolo | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReorgYolo | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Resample | Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Reshape | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ReverseSequence | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| RNN | Not Supported | Supported | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ROIPooling | Supported\* | Supported | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ScaleShift | Supported | Supported\*\*\* | Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ScatterUpdate | Not Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Select | Supported | Supported | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Selu | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| ShuffleChannels | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Sign | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Sin | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Sinh | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| SimplerNMS | Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Slice | Supported | Supported\*\*\* | Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| SoftMax | Supported | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Softplus | Supported | Supported\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Softsign | Supported | Supported\*\* | Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| SpaceToDepth | Not Supported | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| SpatialTransformer | Not Supported | Supported\*\* | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Split | Supported | Supported\*\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Squeeze | Supported | Supported\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| StridedSlice | Supported | Supported\*\* | Not Supported | Supported\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Tan | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| TensorIterator | Not Supported | Supported | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Tile | Supported\*\* | Supported\*\*\* | Not Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| TopK | Supported | Supported\*\* | Not Supported | Supported\*\*\*\* |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Unpooling | Supported | Not Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Unsqueeze | Supported | Supported\*\* | Supported | Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
| Upsampling | Supported | Not Supported | Not Supported | Not Supported |
+--------------------------------+----------------+-----------------+----------------+--------------------+
\* - support is limited to the specific parameters. Refer to "Known Layer Limitations" section for the device :doc:`from the list of supported <openvino_docs_OV_UG_supported_plugins_Supported_Devices>`.
\*\* - support is implemented via :doc:`Extensibility mechanism <openvino_docs_Extensibility_UG_Intro>`.
\*\*\* - supports NCDHW layout.
\*\*\*\* - support is implemented via runtime reference.
@endsphinxdirective

22864
docs/_static/download/operation_conformance_table_files/opset_report_omz_static.html vendored Normal file
View File

File diff suppressed because it is too large Load Diff

3
docs/_static/download/operation_conformance_table_files/template/chosen.jquery.min.js vendored Normal file
View File

File diff suppressed because one or more lines are too long

239
docs/_static/download/operation_conformance_table_files/template/filters.js vendored Normal file
View File

@ -0,0 +1,239 @@
deviceList = [];
$(document).ready(function () {
LoadOpsetNumbers();
LoadDevices();
$('#status').prop("disabled", true);
$("#status").chosen({max_selected_options: 6});
$("#filters").submit(function (event) {
event.preventDefault();
filterTable();
});
$('#reset').click(function () {
$('#opsetNumber').val(0);
$('#operationName').val('');
$('#status').prop("disabled", true).val('');
$('#devices').val(0);
$('#implementation').val(0);
$("#status").chosen("destroy");
$("#status").chosen({max_selected_options: 6});
filterTable();
});
$('#devices').on('change', function () {
if (this.value == 0) {
$('#status').prop("disabled", true).val('');
$("#status").chosen("destroy");
$("#status").chosen({max_selected_options: 6});
} else {
$('#status').prop("disabled", false);
$("#status").chosen("destroy");
$("#status").chosen({max_selected_options: 6});
};
});
});
function LoadOpsetNumbers() {
var data = [];
$('#data th[scope="row"]').each(function () {
num = $(this).text().split("-")[1];
if (data.indexOf(num) < 0) {
data.push(num);
}
});
data.sort();
data = $.map(data, function (item) {
return "<option value=" + item + ">" + item + "</option>";
});
$("#opsetNumber").html('<option value="0">All</option>');
$("#opsetNumber").append(data.join(""));
}
function LoadDevices() {
var data = [];
$('.table-dark.device').each(function () {
if (data.indexOf($(this).text()) < 0) {
data.push($(this).text());
}
});
data.sort();
deviceList = data;
data = $.map(data, function (item) {
return "<option value=" + item + ">" + item + "</option>";
});
$("#devices").html('<option value="0">All</option>');
$("#devices").append(data.join(""));
}
function filterTable() {
device = $("#devices").val();
if (device == 0) {
$("#report td.value, #report td.nr_value, #report td.table-secondary, #report td.table-primary, #report th.table-dark.device").show();
} else {
$("#report td.value, #report td.nr_value, #report td.table-secondary, #report td.table-primary, #report th.table-dark.device").filter(function () {
$(this).toggle($(this).hasClass(device))
});
}
opsetNumber = $("#opsetNumber").val();
operationName = $('#operationName').val().trim();
status = $('#status').val();
implementation = $('#implementation').val();
$("#report #data tr").show();
$('#report').show();
$('#message').hide();
if (opsetNumber != 0) {
$("#report #data tr").filter(function () {
$(this).toggle(checkVersion($(this), opsetNumber));
});
}
if (operationName) {
$("#report #data tr:not(:hidden)").filter(function () {
$(this).toggle($(this).find('th').text().toLowerCase().indexOf(operationName.toLowerCase()) > -1);
});
}
if (implementation != 0) {
if (implementation == 'ni') {
$("#report #data tr:not(:hidden)").filter(function () {
$(this).toggle($(this).find('td').hasClass("value " + device + " not_impl"))
});
} else if (implementation == 'i') {
$("#report #data tr:not(:hidden)").filter(function () {
$(this).toggle($(this).find('td').hasClass("value " + device + " impl"));
});
} else {
$("#report #data tr:not(:hidden)").filter(function () {
$(this).toggle(!$(this).find('td').hasClass("value"));
});
}
}
if (status) {
select = status.split(',');
selector = [];
select.forEach(item => {
if (item == '100p') {
selector.push('.value:visible[crashed="0"][failed="0"][skipped="0"][hanged="0"][value!="---"]');
}
if (item == '100f') {
selector.push('.value:visible[passed="0"][value!="---"]');
}
if (item == 'p') {
selector.push('.value:visible[passed!="0"][value!="---"]');
}
if (item == 'f') {
selector.push('.value:visible[failed!="0"][value!="---"]');
}
if (item == 'c') {
selector.push('.value:visible[crashed!="0"][value!="---"]');
}
if (item == 'h') {
selector.push('.value:visible[hanged!="0"][value!="---"]');
}
if (item == 's') {
selector.push('.value:visible[value!="---"][skipped!="0"]');
}
if (item == 'ex') {
selector.push('.value:visible[value!="---"]');
}
if (item == 'na') {
selector.push('.table-secondary:visible');
}
if (item == 'ns') {
selector.push('.value:visible[value="---"]');
}
});
elements = selector.join(',');
$("#report #data tr:not(:hidden)").filter(function () {
$(this).toggle($(this).find(elements).length > 0)
});
}
if ($("#report #data tr").length == $("#report #data tr:hidden").length) {
$('#report').hide();
$('#message').show();
} else {
calculateStatistics(device);
}
}
function checkVersion(element, opsetNumber) {
var name = element.find('th').text().split("-")[0];
var version = Number(element.find('th').text().split("-")[1]);
var realOpsetNumber = Number(opsetNumber);
if (version > realOpsetNumber) {
return false;
} else {
var versions = [];
$('#report #data tr th[name^="' + name + '-"]').each(function () {
if (Number($(this).text().split('-')[1]) <= realOpsetNumber) {
versions.push(Number(+$(this).text().split('-')[1]));
}
});
return version == Math.max.apply(null, versions);
}
}
function calculateStatistics() {
if (device != 0) {
calculateColumnStatistics(device);
} else {
deviceList.map((el) => calculateColumnStatistics(el))
}
}
function calculateColumnStatistics(device) {
// total
total = $("#report #data tr:not(:hidden)").length;
$('#statistic .table-primary[scope="row"] i').text(total);
// trusted op
count_trusted_op = $("#report #data tr:not(:hidden) ." + device + ".value[value^='100'][crashed='0'][failed='0'][skipped='0']").length;
all_operations = $("#report #data tr:not(:hidden) .value[value!='N/A'][value!='---'][value!='NOT RUN']." + device).length;
if (!all_operations) {
trusted_op = "---";
} else {
trusted_op = (count_trusted_op * 100 / all_operations).toFixed(1) + ' %';
}
$('#statistic .table-primary.' + device + '.trusted-ops').text(trusted_op);
$('#statistic .table-primary.' + device + '.test_total').text(all_operations || 0);
// tested op_counter
tested_op_count = 0;
passed_tested_op_count = 0;
$("#report #data tr:not(:hidden) ." + device + ".value span").each(function () {
text = $(this).text().split(':')[1];
if (text) {
if ($(this).hasClass('green')) {
passed_tested_op_count += +text;
}
tested_op_count += +text;
}
});
// General Pass Rate
if (tested_op_count == 0) {
$('#statistic .table-primary.' + device + '.general_pass_rate').text('---');
} else {
general_pass_rate = (passed_tested_op_count * 100 / tested_op_count).toFixed(1) + ' %';
$('#statistic .table-primary.' + device + '.general_pass_rate').text(general_pass_rate);
}
$('#statistic .table-primary.' + device + '.tested-ops_count').text(tested_op_count);
// AVG Pass Rate
sum_pass_rate = 0;
$("#report #data tr:not(:hidden) ." + device + ".value").each(function () {
if ($(this).attr('value') != 'N/A' && $(this).attr('value') != 'NOT RUN' && $(this).attr('value') != '---') {
sum_pass_rate += +$(this).attr('value');
}
});
if (all_operations == 0) {
$('#statistic .table-primary.' + device + '.avg_pass_rate').text('---');
} else {
avg_pass_rate = (sum_pass_rate / all_operations).toFixed(1) + ' %';
$('#statistic .table-primary.' + device + '.avg_pass_rate').text(avg_pass_rate);
}
}

123
docs/_static/download/operation_conformance_table_files/template/highlight_tables_template.html vendored Normal file
View File

@ -0,0 +1,123 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta http-equiv="X-UA-Compatible" content="ie=edge">
<!-- Bootstrap CSS -->
<link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/4.0.0/css/bootstrap.min.css"
integrity="sha384-Gn5384xqQ1aoWXA+058RXPxPg6fy4IWvTNh0E263XmFcJlSAwiGgFAW/dAiS6JXm" crossorigin="anonymous">
<title>{% block title %}highlight_table{% endblock %}</title>
</head>
<body>
{% block content%}
<h1 class="ml-3 mt-3">Highlights</h1>
<ul class="list-group list-group-flush">
{% for test_mode in expected_test_mode %}
<li class="list-group-item">
{% if expected_test_mode|length > 1 %}
<h3><span class="mr-3">&#9679</span>{{ test_mode }}</h3>
{% endif %}
<table class="table table-hover">
<thead>
<tr>
<th class="table-dark">Plugins</th>
{% for device in devices %}
<th class="table-dark">{{ device }}</th>
{% endfor %}
</tr>
</thead>
<tbody>
<tr>
<td class="table-primary">Total ops pass:</td>
{% for device in devices %}
<td>
{% if device in ops_info[test_mode] %}
<!-- 10(+3)/(205)(-10) -->
{{ ops_info[test_mode][device]['totalPass'] }}
{% if ops_info[test_mode][device]['diffTotalPass'] > 0 %}
(<span class="text-success font-weight-bold">+{{ ops_info[test_mode][device]['diffTotalPass'] }}</span>)
{% elif ops_info[test_mode][device]['diffTotalPass'] < 0 %}
(<span class="text-danger font-weight-bold">{{ ops_info[test_mode][device]['diffTotalPass'] }}</span>)
{% endif %}
/{{ ops_info[test_mode][device]['totalAmount'] }}
{% if ops_info[test_mode][device]['diffTotalAmount'] > 0 %}
(<span class="text-success font-weight-bold">+{{ ops_info[test_mode][device]['diffTotalAmount'] }}</span>)
{% elif ops_info[test_mode][device]['diffTotalAmount'] < 0 %}
(<span class="text-danger font-weight-bold">{{ ops_info[test_mode][device]['diffTotalAmount'] }}</span>)
{% endif %}
{% else %}
NOT RUN
{% endif %}
</td>
{% endfor %}
</tr>
<tr>
<td class="table-primary">Passrate:</td>
{% for device in devices %}
<td>
{% if device in general_pass_rate[test_mode] %}
{{ general_pass_rate[test_mode][device]['current'] }}
{% if general_pass_rate[test_mode][device]['prev'] > 0 %}
(<span class="text-success font-weight-bold">+{{ general_pass_rate[test_mode][device]['prev'] }}</span>)
{% elif general_pass_rate[test_mode][device]['prev'] < 0 %}
(<span class="text-danger font-weight-bold">{{ general_pass_rate[test_mode][device]['prev'] }}</span>)
{% endif %}
%
{% else %}
NOT RUN
{% endif %}
</td>
{% endfor %}
</tr>
</tbody>
</table>
</li>
{% endfor %}
{% if api_info.keys()|length > 0 %}
<li class="list-group-item">
<h3><span class="mr-3">&#9679</span> API </h3>
<table class="table table-hover">
<thead>
<tr>
<th class="table-dark">Plugins</th>
<th class="table-dark">SW Plugins</th>
{% for device in devices %}
<th class="table-dark">{{ device }}</th>
{% endfor %}
</tr>
</thead>
<tbody>
{% for test_type in api_info %}
<td class="table-primary" rowspan="{{ api_info[test_type].keys()|length + 1 }}">{{ test_type }}</td>
{% for sw_plugin in sw_plugins %}
<tr>
<td>{{sw_plugin}}</td>
{% for device in devices %}
{% if device in api_info[test_type][sw_plugin] %}
<td>
{{ api_info[test_type][sw_plugin][device]['passrate'] }}
{% if api_info[test_type][sw_plugin][device]['diff'] > 0 %}
(<span class="text-success font-weight-bold">+{{ api_info[test_type][sw_plugin][device]['diff'] }}</span>)
{% elif api_info[test_type][sw_plugin][device]['diff'] < 0 %}
(<span class="text-danger font-weight-bold">{{ api_info[test_type][sw_plugin][device]['diff'] }}</span>)
{% endif %}
%
</td>
{% else %}
<td>NOT RUN</td>
{% endif %}
{% endfor %}
</tr>
{% endfor %}
{% endfor %}
</tbody>
</table>
</li>
{% endif %}
</ul>
{% endblock %}
</body>
</html>

188
docs/_static/download/operation_conformance_table_files/template/report_template.html vendored Normal file
View File

@ -0,0 +1,188 @@
<!doctype html>
<html lang="en">
<head>
<!-- Required meta tags -->
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
<!-- Bootstrap CSS -->
<link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/4.0.0/css/bootstrap.min.css"
integrity="sha384-Gn5384xqQ1aoWXA+058RXPxPg6fy4IWvTNh0E263XmFcJlSAwiGgFAW/dAiS6JXm" crossorigin="anonymous">
<link rel="stylesheet" href="template/style.css" />
<script src="https://code.jquery.com/jquery-3.2.1.slim.min.js"
integrity="sha384-KJ3o2DKtIkvYIK3UENzmM7KCkRr/rE9/Qpg6aAZGJwFDMVNA/GpGFF93hXpG5KkN"
crossorigin="anonymous"></script>
<script src="template/filters.js"></script>
<script src="template/chosen.jquery.min.js" type="text/javascript"></script>
<title>Report</title>
</head>
<body>
<div class="main">
<h2>Operations coverage summary: Tag: {{report_tag}} | Version: {{report_version}} | Time: {{ timestamp }}</h2>
<div class="legend">
<div>
<span class="table-primary border"></span><span>Collected statistic info</span>
</div>
<div>
<span class="table-secondary border">N/A</span><span>No Tests</span>
</div>
<div>
<span><b>Status:</b></span>
<span class="green">P:85</span><span>Passed</span>
<span class="red">F:0</span><span>Failed</span>
<span class="grey">S:2</span><span>Skipped</span>
<span class="dark">C:0</span><span>Crashed</span>
<span class="grey-red">H:0</span><span>Hanged</span>
</div>
<div>
<span><b>Plugin operation implementation status:</b></span>
<div class="checkmark"></div><div>Implemented</div>
<div class="check"></div><div>Not implemented</div>
</div>
</div>
</div>
<!-- Filters block -->
<div class="filters">
<form id="filters">
<div class="form-group">
<label for="operationName"><b>Operation Name</b></label>
<input id="operationName" type="text" class="form-control" />
</div>
<div class="form-group">
<label for="opsetNumber"><b>Opset Number</b></label>
<select id="opsetNumber" class="form-control"></select>
</div>
<div class="form-group">
<label for="devices"><b>Devices</b></label>
<select id="devices" class="form-control"></select>
</div>
<div class="form-group">
<label for="implementation"><b>Plugin Implementation</b></label>
<select id="implementation" class="form-control">
<option value="0">All</option>
<option value="i">Implemented</option>
<option value="ni">Not implemented</option>
<option value="ns">No status</option>
</select>
</div>
<div class="form-group col-5" style="padding-left:0">
<label for="status"><b>Status</b></label>
<select id="status" class="form-control" multiple>
<option value="100p">100% Passed</option>
<option value="100f">100% Failed</option>
<option value="p">Passed</option>
<option value="f">Failed</option>
<option value="s">Skipped</option>
<option value="c">Crashed</option>
<option value="h">Hanged</option>
<option value="ex">Existing tests</option>
<option value="na">No tests</option>
<option value="ns">No status</option>
</select>
</div>
<button type="submit" class="btn btn-primary">Apply filters</button>
<button type="button" class="btn btn-secondary" id="reset">Reset filters</button>
</form>
</div>
<!-- Results -->
<table class="table table-hover" id="report">
<thead>
<tr>
<th class="table-dark" scope="col" style="position: sticky; top: 97px">Operation</th>
{% for d in devices -%}
<th class="table-dark device {{ d }}" style="position: sticky; top: 97px">{{ d }}</th>
{% endfor %}
</tr>
</thead>
<tbody id="statistic">
<tr>
<th class="table-primary" scope="row">Total: <i>{{ordered_ops|length}}</i></th>
{% for d in devices -%}
<td class="table-primary {{ d }} test_total"> {% if d in covered_ops -%} {{covered_ops[d]}} {% else -%} 0 {% endif -%}</td>
{% endfor %}
</tr>
<tr>
<th class="table-primary" scope="row">Trusted op (passrate=100%):</th>
{% for d in devices -%}
<td class="table-primary {{ d }} trusted-ops">{{trusted_ops[d]}} {% if trusted_ops[d] != "NOT RUN" -%}%{% endif -%}</td>
{% endfor %}
</tr>
<tr>
<th class="table-primary" scope="row">Tested op counter:</th>
{% for d in devices -%}
<td class="table-primary {{ d }} tested-ops_count">{{general_test_count[d]}}</td>
{% endfor %}
</tr>
<tr>
<th class="table-primary" scope="row">AVG passrate per op (=sum_pass_rates/covered_ops_num):</th>
{% for d in devices -%}
<td class="table-primary {{ d }} avg_pass_rate">{{pass_rate_avg[d]}} {% if pass_rate_avg[d] != "NOT RUN" -%}%{% endif -%}</td>
{% endfor %}
</tr>
<tr>
<th class="table-primary" scope="row">General passrate (=passed_tests/all_tests):</th>
{% for d in devices -%}
<td class="table-primary {{ d }} general_pass_rate">{{general_pass_rate[d]}} {% if general_pass_rate[d] != "NOT RUN" -%}%{% endif -%}</td>
{% endfor %}
</tr>
</tbody>
<tbody id="data">
{% for op in ordered_ops -%}
<tr>
<th scope="row" name="{{ op }}">{{ op }}</th>
{% for d in devices -%}
{% if op in results[d] -%}
{% if results[d][op] == "NOT RUN" -%}
<td class="nr_value {{ d }} not_run" title="{{op}} is not run for {{d}} plugin"> NOT RUN</td>
{% else -%}
<td class="value {{ d }} {% if results[d][op].implemented == 'true' -%} impl {% else -%} not_impl {% endif -%}"
passed="{{ results[d][op].passed }}" failed="{{ results[d][op].failed }}"
skipped="{{ results[d][op].skipped }}" crashed="{{ results[d][op].crashed }}"
hanged="{{ results[d][op].hanged }}"
value="{% if (results[d][op].passed != '0' or results[d][op].failed != '0' or results[d][op].crashed != '0' or results[d][op].skipped) != '0' -%}{{ results[d][op].passrate }}{% else -%}---{% endif -%}"
title="{% if results[d][op].implemented == 'true' -%}
{{op}} is implemented in {{d}} plugin
{% else -%}
{{op}} is not implemented in {{d}} plugin
{% endif -%}">
<span class="{% if results[d][op].implemented == 'true' -%} checkmark {% else -%} check {% endif -%}"></span>
{% if (results[d][op].passed != '0' or results[d][op].failed != '0' or results[d][op].crashed != '0' or results[d][op].skipped != '0' or results[d][op].hanged != '0') -%}
{{ results[d][op].passrate }} % <br />
{% else -%}
---<br />
{% endif -%}
<div class="flex">
<div>
{% if (results[d][op].passed != '0' or results[d][op].failed != '0' or results[d][op].crashed != '0' or results[d][op].skipped != '0' or results[d][op].hanged != '0') -%}
<span class="green" title="Passed">P:{{ results[d][op].passed }}</span>
<span class="red" title="Failed">F:{{ results[d][op].failed }}</span>
<span class="grey" title="Skipped">S:{{ results[d][op].skipped }}</span>
<span class="dark" title="Crashed">C:{{ results[d][op].crashed }}</span>
<span class="grey-red" title="Hanged">H:{{ results[d][op].hanged }}</span>
{% else -%}
{% endif -%}
</div>
</div>
</td>
{% endif -%}
{% else -%}
<td class="table-secondary {{ d }}">N/A</td>
{% endif -%}
{% endfor %}
</tr>
{% endfor -%}
</tbody>
</table>
<div id="message" style="display:none">
There is no data related to selected filters. Please set new filters.
</div>
</body>
</html>

619
docs/_static/download/operation_conformance_table_files/template/style.css vendored Normal file
View File

@ -0,0 +1,619 @@
body {
font-size: 14px;
}
.table td, .table th {
padding: .5em .75em;
}
.table td span {
font-size: 0.8em;
}
.value {
font-weight: 500;
}
.value span {
display:inline-block;
font-weight: 400;
padding: 1px 5px;
border-radius: 2px;
cursor: default;
}
.nr_value value {
font-weight: inherit;
background: #8080803d;
}
.nr_value span {
display:inherit;
font-weight: inherit;
padding: inherit;
border-radius: inherit;
cursor: inherit;
}
.green {
background: #0080002e;
}
.red {
background: #ff000038;
}
.grey {
background: #8080803d;
}
.dark {
background: #8b000040;
}
.grey-red {
background: #5e121275;
}
.filters {
background: #FFF;
padding: 5px 10px;
position: sticky;
top: 0;
z-index: 30;
}
.filters form {
display: flex;
background: #efefef;
padding: 10px;
border-radius: 5px;
}
form div{
margin-right: 10px;
}
form button {
align-self: center;
margin-top: 26px;
margin-left: 20px;
}
.main {
margin: 10px;
}
.legend {
display: flex;
}
.legend div {
display:flex;
align-items: center;
margin-right: 20px;
}
.legend span{
display: inline-block;
padding: 3px 5px;
min-height: 25px;
min-width: 25px;
}
.form-group {
margin-bottom: 0;
}
#message {
font-weight: 500;
font-size: 20px;
margin: 20px;
text-align: center;
color: #cf1d1d;
}
.table-dark:hover {
background: #212529!important;
}
h2 {
margin-bottom: 2rem;
}
/* @group Base */
.chosen-container {
position: relative;
display: block;
user-select: none;
}
.chosen-container * {
box-sizing: border-box;
}
.chosen-container .chosen-drop {
position: absolute;
top: 100%;
z-index: 1010;
width: 100%;
border: 1px solid #aaa;
border-top: 0;
background: #fff;
-webkit-box-shadow: 0 4px 5px rgba(0, 0, 0, 0.15);
box-shadow: 0 4px 5px rgba(0, 0, 0, 0.15);
clip: rect(0, 0, 0, 0);
-webkit-clip-path: inset(100% 100%);
clip-path: inset(100% 100%);
}
.chosen-container.chosen-with-drop .chosen-drop {
clip: auto;
-webkit-clip-path: none;
clip-path: none;
}
.chosen-container a {
cursor: pointer;
}
.chosen-container .search-choice .group-name, .chosen-container .chosen-single .group-name {
margin-right: 4px;
overflow: hidden;
white-space: nowrap;
text-overflow: ellipsis;
font-weight: normal;
color: #999999;
}
.chosen-container .search-choice .group-name:after, .chosen-container .chosen-single .group-name:after {
content: ":";
padding-left: 2px;
vertical-align: top;
}
/* @end */
/* @group Single Chosen */
.chosen-container-single .chosen-single {
position: relative;
display: block;
overflow: hidden;
padding: 0 0 0 8px;
height: 25px;
border: 1px solid #aaa;
border-radius: 5px;
background-color: #fff;
background: -webkit-gradient(linear, left top, left bottom, color-stop(20%, #fff), color-stop(50%, #f6f6f6), color-stop(52%, #eee), to(#f4f4f4));
background: linear-gradient(#fff 20%, #f6f6f6 50%, #eee 52%, #f4f4f4 100%);
background-clip: padding-box;
-webkit-box-shadow: 0 0 3px #fff inset, 0 1px 1px rgba(0, 0, 0, 0.1);
box-shadow: 0 0 3px #fff inset, 0 1px 1px rgba(0, 0, 0, 0.1);
color: #444;
text-decoration: none;
white-space: nowrap;
line-height: 24px;
}
.chosen-container-single .chosen-default {
color: #999;
}
.chosen-container-single .chosen-single span {
display: block;
overflow: hidden;
margin-right: 26px;
text-overflow: ellipsis;
white-space: nowrap;
}
.chosen-container-single .chosen-single-with-deselect span {
margin-right: 38px;
}
.chosen-container-single .chosen-single abbr:hover {
background-position: -42px -10px;
}
.chosen-container-single.chosen-disabled .chosen-single abbr:hover {
background-position: -42px -10px;
}
.chosen-container-single .chosen-single div {
position: absolute;
top: 0;
right: 0;
display: block;
width: 18px;
height: 100%;
}
.chosen-container-single .chosen-search {
position: relative;
z-index: 1010;
margin: 0;
padding: 3px 4px;
white-space: nowrap;
}
.chosen-container-single .chosen-drop {
margin-top: -1px;
border-radius: 0 0 4px 4px;
background-clip: padding-box;
}
.chosen-container-single.chosen-container-single-nosearch .chosen-search {
position: absolute;
clip: rect(0, 0, 0, 0);
-webkit-clip-path: inset(100% 100%);
clip-path: inset(100% 100%);
}
/* @end */
/* @group Results */
.chosen-container .chosen-results {
color: #444;
position: relative;
overflow-x: hidden;
overflow-y: auto;
margin: 0 4px 4px 0;
padding: 0 0 0 4px;
max-height: 240px;
-webkit-overflow-scrolling: touch;
}
.chosen-container .chosen-results li {
display: none;
margin: 0;
padding: .75rem;
list-style: none;
line-height: 15px;
word-wrap: break-word;
-webkit-touch-callout: none;
font-size: 1rem;
}
.chosen-container .chosen-results li.active-result {
display: list-item;
cursor: pointer;
}
.chosen-container .chosen-results li.disabled-result {
display: list-item;
color: #ccc;
cursor: default;
}
.chosen-container .chosen-results li.highlighted {
background-color: #007bff;
color: #fff;
}
.chosen-container .chosen-results li.no-results {
color: #777;
display: list-item;
background: #f4f4f4;
}
.chosen-container .chosen-results li.group-result {
display: list-item;
font-weight: bold;
cursor: default;
}
.chosen-container .chosen-results li.group-option {
padding-left: 15px;
}
.chosen-container .chosen-results li em {
font-style: normal;
text-decoration: underline;
}
/* @end */
/* @group Multi Chosen */
.chosen-container-multi .chosen-choices {
position: relative;
overflow: hidden;
margin: 0;
width: 100%;
height: calc(2.25rem + 2px);
box-sizing: border-box;
cursor: text;
padding: .375rem .75rem;
font-size: 0.75rem;
line-height: 1.5;
color: #495057;
background-color: #fff;
background-clip: padding-box;
border: 1px solid #ced4da;
border-radius: .25rem;
transition: border-color .15s ease-in-out,box-shadow .15s ease-in-out;
}
.chosen-container-multi .chosen-choices li {
float: left;
list-style: none;
}
.chosen-container-multi .chosen-choices li.search-field {
margin: 0;
padding: 0;
white-space: nowrap;
}
.chosen-container-multi .chosen-choices li.search-field input[type="text"] {
margin: 1px 0;
padding: 0;
height: auto;
outline: 0;
border: 0 !important;
background: transparent !important;
-webkit-box-shadow: none;
box-shadow: none;
color: #999;
font-size: 1rem;
font-family: sans-serif;
line-height: normal;
border-radius: 0;
width: 25px;
}
.chosen-container-multi .chosen-choices li.search-choice {
position: relative;
margin: 0px 5px 0px 0;
padding: 3px 20px 3px 5px;
border: 1px solid #aaa;
max-width: 100%;
border-radius: 3px;
background-color: #eeeeee;
background-image: -webkit-gradient(linear, left top, left bottom, color-stop(20%, #f4f4f4), color-stop(50%, #f0f0f0), color-stop(52%, #e8e8e8), to(#eee));
background-image: linear-gradient(#f4f4f4 20%, #f0f0f0 50%, #e8e8e8 52%, #eee 100%);
background-size: 100% 19px;
background-repeat: repeat-x;
background-clip: padding-box;
-webkit-box-shadow: 0 0 2px #fff inset, 0 1px 0 rgba(0, 0, 0, 0.05);
box-shadow: 0 0 2px #fff inset, 0 1px 0 rgba(0, 0, 0, 0.05);
color: #333;
line-height: 1rem;
cursor: default;
}
.chosen-container-multi .chosen-choices li.search-choice span {
word-wrap: break-word;
}
.chosen-container-multi .chosen-choices li.search-choice .search-choice-close {
position: absolute;
top: calc( 50% - 6px);
right: 3px;
display: block;
width: 12px;
height: 12px;
}
.chosen-container-multi .chosen-choices li.search-choice .search-choice-close:before {
content: "";
width: 0;
height: 12px;
border-left: 2px solid #555;
position: absolute;
top: 0;
left: 50%;
transform: rotate(45deg);
}
.chosen-container-multi .chosen-choices li.search-choice .search-choice-close:after {
content:"";
width: 0;
height: 12px;
border-left: 2px solid #555;
position: absolute;
top: 0;
left: 50%;
transform: rotate(-45deg);
}
.chosen-container-multi .chosen-choices li.search-choice .search-choice-close:hover {
background-position: -42px -10px;
}
.chosen-container-multi .chosen-choices li.search-choice-disabled {
padding-right: 5px;
border: 1px solid #ccc;
background-color: #e4e4e4;
background-image: -webkit-gradient(linear, left top, left bottom, color-stop(20%, #f4f4f4), color-stop(50%, #f0f0f0), color-stop(52%, #e8e8e8), to(#eee));
background-image: linear-gradient(#f4f4f4 20%, #f0f0f0 50%, #e8e8e8 52%, #eee 100%);
color: #666;
}
.chosen-container-multi .chosen-choices li.search-choice-focus {
background: #d4d4d4;
}
.chosen-container-multi .chosen-choices li.search-choice-focus .search-choice-close {
background-position: -42px -10px;
}
.chosen-container-multi .chosen-results {
margin: 0;
padding: 0;
}
.chosen-container-multi .chosen-drop .result-selected {
display: list-item;
color: #ccc;
cursor: default;
}
/* @end */
/* @group Active */
.chosen-container-active .chosen-single {
border: 1px solid #5897fb;
-webkit-box-shadow: 0 0 5px rgba(0, 0, 0, 0.3);
box-shadow: 0 0 5px rgba(0, 0, 0, 0.3);
}
.chosen-container-active.chosen-with-drop .chosen-single {
border: 1px solid #aaa;
border-bottom-right-radius: 0;
border-bottom-left-radius: 0;
background-image: -webkit-gradient(linear, left top, left bottom, color-stop(20%, #eee), color-stop(80%, #fff));
background-image: linear-gradient(#eee 20%, #fff 80%);
-webkit-box-shadow: 0 1px 0 #fff inset;
box-shadow: 0 1px 0 #fff inset;
}
.chosen-container-active.chosen-with-drop .chosen-single div {
border-left: none;
background: transparent;
}
.chosen-container-active.chosen-with-drop .chosen-single div b {
background-position: -18px 2px;
}
.chosen-container-active .chosen-choices {
border: 1px solid #80bdff;
box-shadow:0 0 0 0.2rem rgb(0 123 255 / 25%)
}
.chosen-container-active .chosen-choices li.search-field input[type="text"] {
color: #222 !important;
}
/* @end */
/* @group Disabled Support */
.chosen-disabled {
opacity: 0.5 !important;
cursor: default;
}
.chosen-disabled .chosen-single {
cursor: default;
}
.chosen-disabled .chosen-choices .search-choice .search-choice-close {
cursor: default;
}
/* @end */
/* @group Right to Left */
.chosen-rtl {
text-align: right;
}
.chosen-rtl .chosen-single {
overflow: visible;
padding: 0 8px 0 0;
}
.chosen-rtl .chosen-single span {
margin-right: 0;
margin-left: 26px;
direction: rtl;
}
.chosen-rtl .chosen-single-with-deselect span {
margin-left: 38px;
}
.chosen-rtl .chosen-single div {
right: auto;
left: 3px;
}
.chosen-rtl .chosen-single abbr {
right: auto;
left: 26px;
}
.chosen-rtl .chosen-choices li {
float: right;
}
.chosen-rtl .chosen-choices li.search-field input[type="text"] {
direction: rtl;
}
.chosen-rtl .chosen-choices li.search-choice {
margin: 3px 5px 3px 0;
padding: 3px 5px 3px 19px;
}
.chosen-rtl .chosen-choices li.search-choice .search-choice-close {
right: auto;
left: 4px;
}
.chosen-rtl.chosen-container-single .chosen-results {
margin: 0 0 4px 4px;
padding: 0 4px 0 0;
}
.chosen-rtl .chosen-results li.group-option {
padding-right: 15px;
padding-left: 0;
}
.chosen-rtl.chosen-container-active.chosen-with-drop .chosen-single div {
border-right: none;
}
.chosen-rtl.chosen-container-single .chosen-single div b {
background-position: 6px 2px;
}
.chosen-rtl.chosen-container-single.chosen-with-drop .chosen-single div b {
background-position: -12px 2px;
}
.check {
width: 16px;
height: 16px;
background: #be2d2d;
text-indent: -1000;
border-radius: 8px;
position: relative;
}
.check::before {
display: block;
border-bottom: 2px solid #FFF;
position: absolute;
z:index: 10;
width: 8px;
top:7px;
left: 4px;
content: "";
}
.checkmark {
display: block;
width: 16px;
height: 16px;
position: relative;
}
.checkmark::before {
position: absolute;
display: block;
width: 2px;
height: 16px;
background-color: green;
left: 10px;
content: '';
top: 0px;
z-index: 20;
transform: rotate(45deg);
}
.checkmark::after {
position: absolute;
width: 2px;
content: '';
height: 7px;
background-color: green;
left:3px;
display: block;
top: 7px;
z-index: 20;
transform: rotate(-45deg);
}
.flex {
display: flex;
justify-content: space-between;
}
.not_impl:hover {
background: #ffdee1;
}
.impl:hover {
background: #e0fde6;
}
.not_run:hover {
background: #8b000040;
}

72
docs/resources/Supported_Devices.md Normal file
View File

@ -0,0 +1,72 @@
# Supported Devices {#openvino_docs_OV_UG_supported_plugins_Supported_Devices}
@sphinxdirective
The OpenVINO runtime can infer various models of different input and output formats. Here, you can find configurations
supported by OpenVINO devices, which are CPU, GPU, and GNA (Gaussian Neural Accelerator coprocessor).
Currently, processors of the 11th generation and later (up to the 13th generation at the moment) provide a further performance boost, especially with INT8 models.
.. note::
With OpenVINO™ 2023.0 release, support has been cancelled for all VPU accelerators based on Intel® Movidius™.
+---------------------------------------------------------------------+------------------------------------------------------------------------------------------------------+
| OpenVINO Device | Supported Hardware |
+=====================================================================+======================================================================================================+
|| :doc:`CPU <openvino_docs_OV_UG_supported_plugins_CPU>` | Intel® Xeon® with Intel® Advanced Vector Extensions 2 (Intel® AVX2), Intel® Advanced Vector |
|| (x86) | Extensions 512 (Intel® AVX-512), Intel® Advanced Matrix Extensions (Intel® AMX), |
|| | Intel® Core™ Processors with Intel® AVX2, |
|| | Intel® Atom® Processors with Intel® Streaming SIMD Extensions (Intel® SSE) |
|| | |
|| (Arm®) | Raspberry Pi™ 4 Model B, Apple® Mac mini with M1 chip, NVIDIA® Jetson Nano™, Android™ devices |
|| | |
+---------------------------------------------------------------------+------------------------------------------------------------------------------------------------------+
|| :doc:`GPU <openvino_docs_OV_UG_supported_plugins_GPU>` | Intel® Processor Graphics including Intel® HD Graphics and Intel® Iris® Graphics, |
|| | Intel® Arc™ A-Series Graphics, Intel® Data Center GPU Flex Series, Intel® Data Center GPU Max Series |
+---------------------------------------------------------------------+------------------------------------------------------------------------------------------------------+
|| :doc:`GNA plugin <openvino_docs_OV_UG_supported_plugins_GNA>` | Intel® Speech Enabling Developer Kit, Amazon Alexa* Premium Far-Field Developer Kit, Intel® |
|| (available in the Intel® Distribution of OpenVINO™ toolkit) | Pentium® Silver J5005 Processor, Intel® Pentium® Silver N5000 Processor, Intel® |
|| | Celeron® J4005 Processor, Intel® Celeron® J4105 Processor, Intel® Celeron® |
|| | Processor N4100, Intel® Celeron® Processor N4000, Intel® Core™ i3-8121U Processor, |
|| | Intel® Core™ i7-1065G7 Processor, Intel® Core™ i7-1060G7 Processor, Intel® |
|| | Core™ i5-1035G4 Processor, Intel® Core™ i5-1035G7 Processor, Intel® Core™ |
|| | i5-1035G1 Processor, Intel® Core™ i5-1030G7 Processor, Intel® Core™ i5-1030G4 Processor, |
|| | Intel® Core™ i3-1005G1 Processor, Intel® Core™ i3-1000G1 Processor, |
|| | Intel® Core™ i3-1000G4 Processor |
+---------------------------------------------------------------------+------------------------------------------------------------------------------------------------------+
Beside inference using a specific device, OpenVINO offers three inference modes for automated inference management. These are:
* :doc:`Automatic Device Selection <openvino_docs_OV_UG_supported_plugins_AUTO>` - automatically selects the best device
available for the given task. It offers many additional options and optimizations, including inference on
multiple devices at the same time.
* :doc:`Multi-device Inference <openvino_docs_OV_UG_Running_on_multiple_devices>` - executes inference on multiple devices.
Currently, this mode is considered a legacy solution. Using Automatic Device Selection is advised.
* :doc:`Heterogeneous Inference <openvino_docs_OV_UG_Hetero_execution>` - enables splitting inference among several devices
automatically, for example, if one device doesn’t support certain operations.
Devices similar to the ones we have used for benchmarking can be accessed using `Intel® DevCloud for the Edge <https://devcloud.intel.com/edge/>`__,
a remote development environment with access to Intel® hardware and the latest versions of the Intel® Distribution
of OpenVINO™ Toolkit. `Learn more <https://devcloud.intel.com/edge/get_started/devcloud/>`__ or `Register here <https://inteliot.force.com/DevcloudForEdge/s/>`__.
To learn more about each of the supported devices and modes, refer to the sections of:
* :doc:`Inference Device Support <openvino_docs_OV_UG_Working_with_devices>`
* :doc:`Inference Modes <openvino_docs_Runtime_Inference_Modes_Overview>`
For setting relevant configuration, refer to the
:doc:`Integrate with Customer Application <openvino_docs_OV_UG_Integrate_OV_with_your_application>`
topic (step 3 "Configure input and output").
@endsphinxdirective

9
docs/resources/resources.md
View File

@ -16,7 +16,8 @@
openvino_docs_OV_UG_supported_plugins_Supported_Devices
openvino_supported_models
openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers
openvino_resources_supported_operations
openvino_resources_supported_operations_frontend
.. toctree::
:maxdepth: 1
@ -35,9 +36,11 @@ and its proprietary model format, OpenVINO IR.
:doc:`Supported Devices <openvino_docs_OV_UG_supported_plugins_Supported_Devices>` is compatibility information about supported hardware accelerators.
:doc:`Supported Models <openvino_supported_models>` is a table of models officially supported by OpenVINO.
:doc:`Supported Models <openvino_supported_models>` is a table of models officially supported by OpenVINO.
:doc:`Supported Framework Layers <openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers>` are lists of framework layers supported by OpenVINO.
:doc:`Supported Operations <openvino_resources_supported_operations>` is a listing of framework layers supported by OpenVINO.
:doc:`Supported Operations <openvino_resources_supported_operations_frontend>` is a listing of layers supported by OpenVINO inference devices.
:doc:`Glossary <openvino_docs_OV_Glossary>` contains terms used in OpenVINO.

1140
docs/resources/supported_operations_framework_frontend.md Normal file
View File

File diff suppressed because it is too large Load Diff

171
docs/resources/supported_operations_inference_devices.md Normal file
View File

@ -0,0 +1,171 @@
# Supported Operations - by Inference Devices {#openvino_resources_supported_operations}
@sphinxdirective
This page lists operations supported by OpenVINO inference devices. The table presents general information,
for a more detailed and most recent listing of operations that are implemented and tested:
.. button-link:: _static/download/operation_conformance_table_files/opset_report_omz_static.html
:color: primary
:outline:
See the full conformance report table
================================= =============== ============== ================ ==================
Operations CPU (x86) GPU GNA CPU (Arm®)
================================= =============== ============== ================ ==================
Abs Supported** Supported Not Supported Supported
Acos Supported** Supported Not Supported Supported****
Acosh Supported** Supported Not Supported Supported****
Activation-Clamp Supported*** Supported Supported Supported
Activation-ELU Supported*** Supported Not Supported Supported
Activation-Exp Supported*** Supported Supported Supported
Activation-Leaky ReLU Supported*** Supported Supported Not Supported
Activation-Not Supported*** Supported Not Supported Not Supported
Activation-PReLU Supported*** Supported Not Supported Supported
Activation-ReLU Supported*** Supported Supported Supported
Activation-ReLU6 Supported*** Supported Not Supported Not Supported
Activation-Sigmoid/Logistic Supported*** Supported Supported Supported
Activation-TanH Supported*** Supported Supported Supported
ArgMax Supported** Supported Not Supported Not Supported
Asin Supported** Supported Not Supported Supported****
Asinh Supported** Supported Not Supported Supported****
Atan Supported** Supported Not Supported Supported****
Atanh Supported** Supported Not Supported Supported****
BatchNormalization Supported Supported Not Supported Supported
BinaryConvolution Supported Supported Not Supported Not Supported
Broadcast Supported** Supported Not Supported Supported
Ceil Supported** Supported Not Supported Supported
Concat Supported*** Supported Supported Supported
Const Supported Supported Supported Supported
Convolution-Dilated Supported Supported Not Supported Supported
Convolution-Dilated 3D Supported Supported Not Supported Not Supported
Convolution-Grouped Supported Supported Not Supported Supported
Convolution-Grouped 3D Supported Supported Not Supported Not Supported
Convolution-Ordinary Supported Supported Supported* Supported
Convolution-Ordinary 3D Supported Supported Not Supported Not Supported
Cos Supported** Supported Not Supported Supported****
Cosh Supported** Supported Not Supported Supported****
Crop Supported Supported Supported Not Supported
CTCGreedyDecoder Supported** Supported** Not Supported Supported****
Deconvolution Supported Supported Not Supported Not Supported
Deconvolution 3D Supported Supported Not Supported Not Supported
DeformableConvolution Supported Supported Not Supported Not Supported
DepthToSpace Supported** Supported Not Supported Supported*
DetectionOutput Supported** Supported Not Supported Supported****
Eltwise-And Supported*** Supported Not Supported Supported
Eltwise-Add Supported*** Supported Not Supported Supported
Eltwise-Div Supported*** Supported Not Supported Supported
Eltwise-Equal Supported*** Supported Not Supported Supported*
Eltwise-FloorMod Supported*** Supported Not Supported Supported****
Eltwise-Greater Supported*** Supported Not Supported Supported
Eltwise-GreaterEqual Supported*** Supported Not Supported Supported
Eltwise-Less Supported*** Supported Not Supported Supported*
Eltwise-LessEqual Supported*** Supported Not Supported Supported*
Eltwise-LogicalAnd Supported*** Supported Not Supported Supported
Eltwise-LogicalOr Supported*** Supported Not Supported Supported
Eltwise-LogicalXor Supported*** Supported Not Supported Supported
Eltwise-Max Supported*** Supported Not Supported Supported
Eltwise-Min Supported*** Supported Not Supported Supported
Eltwise-Mul Supported*** Supported Supported Supported
Eltwise-NotEqual Supported*** Supported Not Supported Supported*
Eltwise-Pow Supported*** Supported Not Supported Supported
Eltwise-Prod Supported*** Supported Supported Not Supported
Eltwise-SquaredDiff Supported*** Supported Not Supported Supported
Eltwise-Sub Supported*** Supported Supported Supported
Eltwise-Sum Supported*** Supported Supported Supported****
Erf Supported** Supported Not Supported Supported****
Exp Supported Supported Supported Supported
FakeQuantize Supported Not Supported Not Supported Supported*
Fill Supported** Not Supported Not Supported Not Supported
Flatten Supported Supported Not Supported Not Supported
Floor Supported** Supported Not Supported Supported
FullyConnected (Inner Product) Supported*** Supported Supported Supported
Gather Supported** Supported Not Supported Supported*
GatherTree Supported** Not Supported Not Supported Supported****
Gemm Supported Supported Not Supported Not Supported
GRN Supported** Supported** Not Supported Supported
HardSigmoid Supported** Supported Not Supported Supported****
Interp Supported** Supported** Not Supported Supported*
Log Supported** Supported Supported Supported
LRN (Norm) Supported Supported Not Supported Supported*
LSTMCell Supported Supported Supported Supported
GRUCell Supported Supported Supported Supported
RNNCell Supported Supported Not Supported Supported
LSTMSequence Supported Supported Supported Supported****
GRUSequence Supported Supported Supported Supported****
RNNSequence Supported Supported Not Supported Supported****
LogSoftmax Supported** Supported Not Supported Supported
Memory Supported Not Supported Supported Not Supported
MVN Supported** Supported Not Supported Supported*
Neg Supported** Supported Not Supported Supported
NonMaxSuppression Supported** Not Supported Not Supported Supported****
Normalize Supported** Supported Not Supported Supported*
OneHot Supported** Supported Not Supported Supported****
Pad Supported** Supported Not Supported Supported*
Permute Supported Supported Supported* Not Supported
Pooling(AVG,MAX) Supported Supported Supported Supported
Pooling(AVG,MAX) 3D Supported Supported Not Supported Supported*
Power Supported** Supported Supported* Supported
PowerFile Supported** Not Supported Not Supported Not Supported
PriorBox Supported** Supported Not Supported Supported
PriorBoxClustered Supported** Supported** Not Supported Supported
Proposal Supported** Supported Not Supported Supported****
PSROIPooling Supported** Supported Not Supported Supported****
Range Supported** Not Supported Not Supported Not Supported
Reciprocal Supported** Supported Not Supported Not Supported
ReduceAnd Supported** Supported Not Supported Supported****
ReduceL1 Supported** Supported Not Supported Supported
ReduceL2 Supported** Supported Not Supported Supported
ReduceLogSum Supported** Supported Not Supported Supported
ReduceLogSumExp Supported** Supported Not Supported Not Supported
ReduceMax Supported** Supported Not Supported Supported
ReduceMean Supported** Supported Not Supported Supported
ReduceMin Supported** Supported Not Supported Supported
ReduceOr Supported** Supported Not Supported Supported****
ReduceProd Supported** Supported Not Supported Supported
ReduceSum Supported** Supported Not Supported Supported
ReduceSumSquare Supported** Supported Not Supported Not Supported
RegionYolo Supported** Supported Not Supported Supported****
ReorgYolo Supported** Supported Not Supported Supported
Resample Supported** Supported Not Supported Not Supported
Reshape Supported*** Supported Supported Supported
ReverseSequence Supported** Supported Not Supported Supported****
RNN Supported Not Supported Not Supported Supported
ROIPooling Supported Supported* Not Supported Supported****
ScaleShift Supported*** Supported Supported Not Supported
ScatterUpdate Supported** Not Supported Not Supported Not Supported
Select Supported Supported Not Supported Supported
Selu Supported** Supported Not Supported Supported****
ShuffleChannels Supported** Supported Not Supported Supported
Sign Supported** Supported Not Supported Supported
Sin Supported** Supported Not Supported Supported
Sinh Supported** Supported Not Supported Supported****
SimplerNMS Supported** Supported Not Supported Not Supported
Slice Supported*** Supported Supported Not Supported
SoftMax Supported*** Supported Not Supported Supported
Softplus Supported** Supported Not Supported Supported
Softsign Supported** Supported Supported Not Supported
SpaceToDepth Supported** Not Supported Not Supported Supported*
SpatialTransformer Supported** Not Supported Not Supported Not Supported
Split Supported*** Supported Supported Supported
Squeeze Supported** Supported Supported Supported
StridedSlice Supported** Supported Not Supported Supported*
Tan Supported** Supported Not Supported Supported****
TensorIterator Supported Not Supported Supported Supported
Tile Supported*** Supported** Not Supported Supported
TopK Supported** Supported Not Supported Supported****
Unpooling Not Supported Supported Not Supported Not Supported
Unsqueeze Supported** Supported Supported Supported
Upsampling Not Supported Supported Not Supported Not Supported
================================= =============== ============== ================ ==================
| `*` - support is limited to the specific parameters. Refer to "Known Layer Limitations" section for the device :doc:`from the list of supported <openvino_docs_OV_UG_supported_plugins_Supported_Devices>`.
| `**` - support is implemented via :doc:`Extensibility mechanism <openvino_docs_Extensibility_UG_Intro>`.
| `***` - supports NCDHW layout.
| `****` - support is implemented via runtime reference.
@endsphinxdirective