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

ONNX LSTM fix get_shape error (#3033)

Browse Source 
* ONNX LSTM get dimension only if required

* Test dynamic onnx lstm model import

* Enable LSTM_Seq_lens_unpacked_model import test

* Disable model zoo execution test "MSFT_opset9_LSTM_Seq_lens_unpacked"

* Add missed comma in xfail list

* Update error messages

* init xfail issue

* test zoo models import xfail issue

* Fix SEQ_LENGTH init

* Comments update

* Fix usage of v0::Add by overloaded operator
This commit is contained in:
Katarzyna Mitrus 2020-11-13 15:31:29 +01:00 committed by GitHub
parent 18f04860af
commit 8dbff709fb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 478 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

208
ngraph/frontend/onnx_import/src/op/lstm.cpp
View File

@ -60,10 +60,61 @@ namespace ngraph
LSTM_INPUT_P LSTM_INPUT_P
}; };
enum class LSTMInputDimension
{
BATCH_SIZE,
SEQ_LENGTH,
NUM_DIRECTIONS,
HIDDEN_SIZE,
};
struct LSTMNgInputMap struct LSTMNgInputMap
{ {
using container_type = std::map<LSTMInput, Output<ngraph::Node>>; // Check if input shape dimension at dimension_index is static
using iterator = typename container_type::iterator; bool check_static_input_dim(LSTMInput input, const size_t dimension_index)
{
return m_input_map[input].get_partial_shape().rank().is_static() &&
m_input_map[input].get_partial_shape().rank().get_length() >
dimension_index &&
m_input_map[input].get_partial_shape()[dimension_index].is_static();
}
// Validate and handle dimensions required to create default inputs
void init_dim_map()
{
// batch_size
if (check_static_input_dim(LSTMInput::LSTM_INPUT_X, 0))
{
m_dim_map[LSTMInputDimension::BATCH_SIZE] =
m_input_map[LSTMInput::LSTM_INPUT_X]
.get_partial_shape()[0]
.get_length();
}
// seq_length
if (check_static_input_dim(LSTMInput::LSTM_INPUT_X, 1))
{
m_dim_map[LSTMInputDimension::SEQ_LENGTH] =
m_input_map[LSTMInput::LSTM_INPUT_X]
.get_partial_shape()[1]
.get_length();
}
// num_directions
if (check_static_input_dim(LSTMInput::LSTM_INPUT_R, 0))
{
m_dim_map[LSTMInputDimension::NUM_DIRECTIONS] =
m_input_map[LSTMInput::LSTM_INPUT_R]
.get_partial_shape()[0]
.get_length();
}
// hidden_size
if (check_static_input_dim(LSTMInput::LSTM_INPUT_R, 2))
{
m_dim_map[LSTMInputDimension::HIDDEN_SIZE] =
m_input_map[LSTMInput::LSTM_INPUT_R]
.get_partial_shape()[2]
.get_length();
}
}
explicit LSTMNgInputMap(const Node& node) explicit LSTMNgInputMap(const Node& node)
{ {
@ -74,99 +125,169 @@ namespace ngraph
constexpr std::size_t peepholes_count{3}; constexpr std::size_t peepholes_count{3};
// ----- Mandatory inputs ------ // ----- Mandatory inputs ------
// Packed input sequences. Shape: [seq_length, batch_size, input_size] // Packed input sequences.
m_map[LSTMInput::LSTM_INPUT_X] = // ONNX Shape: [seq_length, batch_size, input_size]
// OpenVino Shape: [batch_size, seq_length, input_size]
m_input_map[LSTMInput::LSTM_INPUT_X] =
builder::opset1::reorder_axes(ng_inputs.at(0), {1, 0, 2}); builder::opset1::reorder_axes(ng_inputs.at(0), {1, 0, 2});
// Weight tensor for the gates. // Weight tensor for the gates.
// Shape: [num_directions, 4*hidden_size, input_size] // Shape: [num_directions, 4*hidden_size, input_size]
m_map[LSTMInput::LSTM_INPUT_W] = ngraph::op::util::convert_lstm_node_format( m_input_map[LSTMInput::LSTM_INPUT_W] =
ngraph::op::util::convert_lstm_node_format(
ng_inputs.at(1), ng_inputs.at(1),
ngraph::op::util::LSTMWeightsFormat::IOFC, ngraph::op::util::LSTMWeightsFormat::IOFC,
ngraph::op::util::LSTMWeightsFormat::FICO, ngraph::op::util::LSTMWeightsFormat::FICO,
1); 1);
// The recurrence weight tensor. // The recurrence weight tensor.
// Shape: [num_directions, 4*hidden_size, hidden_size] // Shape: [num_directions, 4*hidden_size, hidden_size]
m_map[LSTMInput::LSTM_INPUT_R] = ngraph::op::util::convert_lstm_node_format( m_input_map[LSTMInput::LSTM_INPUT_R] =
ngraph::op::util::convert_lstm_node_format(
ng_inputs.at(2), ng_inputs.at(2),
ngraph::op::util::LSTMWeightsFormat::IOFC, ngraph::op::util::LSTMWeightsFormat::IOFC,
ngraph::op::util::LSTMWeightsFormat::FICO, ngraph::op::util::LSTMWeightsFormat::FICO,
1); 1);
const std::size_t hidden_size = // Get dimensions needed for default inputs creation
m_map[LSTMInput::LSTM_INPUT_R].get_shape().back(); init_dim_map();
const std::size_t batch_size =
m_map[LSTMInput::LSTM_INPUT_X].get_shape().at(0);
const std::size_t num_directions =
m_map[LSTMInput::LSTM_INPUT_W].get_shape().front();
// ------ Optional inputs ------ // ------ Optional inputs ------
// The bias tensor for input gate. Shape [num_directions, 4*hidden_size] // `B` - The bias tensor for input gate.
// ONNX Shape: [num_directions, 8*hidden_size]
// OpenVino Shape: [num_directions, 4*hidden_size]
if (ng_inputs.size() > 3 && !ngraph::op::is_null(ng_inputs.at(3))) if (ng_inputs.size() > 3 && !ngraph::op::is_null(ng_inputs.at(3)))
{ {
auto bias = ng_inputs.at(3); auto bias = ng_inputs.at(3);
auto split_bias = builder::opset1::split(bias, 2, 1); auto split_bias = builder::opset1::split(bias, 2, 1);
NGRAPH_SUPPRESS_DEPRECATED_START NGRAPH_SUPPRESS_DEPRECATED_START
m_map[LSTMInput::LSTM_INPUT_B] = split_bias.at(0) + split_bias.at(1); m_input_map[LSTMInput::LSTM_INPUT_B] =
std::make_shared<default_opset::Add>(split_bias.at(0),
split_bias.at(1));
NGRAPH_SUPPRESS_DEPRECATED_END NGRAPH_SUPPRESS_DEPRECATED_END
m_map[LSTMInput::LSTM_INPUT_B] = m_input_map[LSTMInput::LSTM_INPUT_B] =
ngraph::op::util::convert_lstm_node_format( ngraph::op::util::convert_lstm_node_format(
m_map[LSTMInput::LSTM_INPUT_B], m_input_map[LSTMInput::LSTM_INPUT_B],
ngraph::op::util::LSTMWeightsFormat::IOFC, ngraph::op::util::LSTMWeightsFormat::IOFC,
ngraph::op::util::LSTMWeightsFormat::FICO, ngraph::op::util::LSTMWeightsFormat::FICO,
1); 1);
} }
else else
{ {
m_map[LSTMInput::LSTM_INPUT_B] = default_opset::Constant::create( NGRAPH_CHECK(m_dim_map.count(LSTMInputDimension::NUM_DIRECTIONS) &&
element::f32, m_dim_map.count(LSTMInputDimension::HIDDEN_SIZE),
Shape{num_directions, gates_count * hidden_size}, "ONNX LSTM: Can't create default `B` input, "
std::vector<float>(num_directions * gates_count * hidden_size, "because at least one of required dimensions "
"(num_directions, hidden_size) is dynamic. "
"\n`R` input onnx shape {num_directions, "
"gates_count*hidden_size, hidden_size}: ",
ng_inputs.at(2).get_partial_shape());
m_input_map[LSTMInput::LSTM_INPUT_B] = default_opset::Constant::create(
m_input_map[LSTMInput::LSTM_INPUT_X].get_element_type(),
Shape{m_dim_map[LSTMInputDimension::NUM_DIRECTIONS],
gates_count * m_dim_map[LSTMInputDimension::HIDDEN_SIZE]},
std::vector<float>(m_dim_map[LSTMInputDimension::NUM_DIRECTIONS] *
gates_count *
m_dim_map[LSTMInputDimension::HIDDEN_SIZE],
0.f)); 0.f));
} }
// The lengths of the sequences in a batch. Shape [batch_size] // `sequence_lens`- The lengths of the sequences in a batch.
// Shape: [batch_size]
if (ng_inputs.size() > 4 && !ngraph::op::is_null(ng_inputs.at(4))) if (ng_inputs.size() > 4 && !ngraph::op::is_null(ng_inputs.at(4)))
{ {
m_map[LSTMInput::LSTM_INPUT_SEQ_LENGTHS] = ng_inputs.at(4); m_input_map[LSTMInput::LSTM_INPUT_SEQ_LENGTHS] = ng_inputs.at(4);
} }
else else
{ {
m_map[LSTMInput::LSTM_INPUT_SEQ_LENGTHS] = NGRAPH_CHECK(
m_dim_map.count(LSTMInputDimension::BATCH_SIZE) &&
m_dim_map.count(LSTMInputDimension::SEQ_LENGTH),
"ONNX LSTM: Can't create default `sequence_lens` input, ",
"because at least one of required dimensions "
"(batch_size, seq_length) is dynamic. "
"\n`X` input onnx shape {seq_length, batch_size, input_size} is ",
ng_inputs.at(0).get_partial_shape());
m_input_map[LSTMInput::LSTM_INPUT_SEQ_LENGTHS] =
default_opset::Constant::create( default_opset::Constant::create(
element::i32, element::i32,
Shape{batch_size}, Shape{m_dim_map[LSTMInputDimension::BATCH_SIZE]},
std::vector<std::int32_t>( std::vector<std::int32_t>(
batch_size, m_dim_map[LSTMInputDimension::BATCH_SIZE],
m_map[LSTMInput::LSTM_INPUT_X].get_shape().at(1))); m_dim_map[LSTMInputDimension::SEQ_LENGTH]));
} }
// The initial value of the hidden. // `initial_h` - The initial value of the hidden.
// Shape [num_directions, batch_size, hidden_size] // ONNX Shape: [num_directions, batch_size, hidden_size]
// OpenVino Shape: [batch_size, num_directions, hidden_size]
if (ng_inputs.size() > 5 && !ngraph::op::is_null(ng_inputs.at(5))) if (ng_inputs.size() > 5 && !ngraph::op::is_null(ng_inputs.at(5)))
{ {
m_map[LSTMInput::LSTM_INPUT_INIT_H] = m_input_map[LSTMInput::LSTM_INPUT_INIT_H] =
builder::opset1::reorder_axes(ng_inputs.at(5), {1, 0, 2}); builder::opset1::reorder_axes(ng_inputs.at(5), {1, 0, 2});
} }
else else
{ {
m_map[LSTMInput::LSTM_INPUT_INIT_H] = default_opset::Constant::create( NGRAPH_CHECK(
element::f32, m_dim_map.count(LSTMInputDimension::BATCH_SIZE) &&
Shape{batch_size, num_directions, hidden_size}, m_dim_map.count(LSTMInputDimension::NUM_DIRECTIONS) &&
std::vector<float>(batch_size * num_directions * hidden_size, 0.f)); m_dim_map.count(LSTMInputDimension::HIDDEN_SIZE),
"ONNX LSTM: Can't create default `initial_h` input, "
"because at least one of required dimensions "
"(batch_size, num_directions, hidden_size) is dynamic. "
"\n`X` input onnx shape {seq_length, batch_size, input_size} is ",
ng_inputs.at(0).get_partial_shape(),
"\n`R` input onnx shape {num_directions, 4*hidden_size, "
"hidden_size} is ",
ng_inputs.at(2).get_partial_shape());
m_input_map[LSTMInput::LSTM_INPUT_INIT_H] =
default_opset::Constant::create(
m_input_map[LSTMInput::LSTM_INPUT_X].get_element_type(),
Shape{m_dim_map[LSTMInputDimension::BATCH_SIZE],
m_dim_map[LSTMInputDimension::NUM_DIRECTIONS],
m_dim_map[LSTMInputDimension::HIDDEN_SIZE]},
std::vector<float>(
m_dim_map[LSTMInputDimension::BATCH_SIZE] *
m_dim_map[LSTMInputDimension::NUM_DIRECTIONS] *
m_dim_map[LSTMInputDimension::HIDDEN_SIZE],
0.f));
} }
// The initial value of the cell. // `initial_c` - The initial value of the cell.
// Shape [num_directions, batch_size, hidden_size] // ONNX Shape: [num_directions, batch_size, hidden_size]
// OpenVino Shape: [batch_size, num_directions, hidden_size]
if (ng_inputs.size() > 6 && !ngraph::op::is_null(ng_inputs.at(6))) if (ng_inputs.size() > 6 && !ngraph::op::is_null(ng_inputs.at(6)))
{ {
m_map[LSTMInput::LSTM_INPUT_INIT_C] = m_input_map[LSTMInput::LSTM_INPUT_INIT_C] =
builder::opset1::reorder_axes(ng_inputs.at(6), {1, 0, 2}); builder::opset1::reorder_axes(ng_inputs.at(6), {1, 0, 2});
} }
else else
{ {
m_map[LSTMInput::LSTM_INPUT_INIT_C] = default_opset::Constant::create( NGRAPH_CHECK(
element::f32, m_dim_map.count(LSTMInputDimension::BATCH_SIZE) &&
Shape{batch_size, num_directions, hidden_size}, m_dim_map.count(LSTMInputDimension::NUM_DIRECTIONS) &&
std::vector<float>(batch_size * num_directions * hidden_size, 0.f)); m_dim_map.count(LSTMInputDimension::HIDDEN_SIZE),
"ONNX LSTM: Can't create default `initial_c` input, "
"because at least one of required dimensions "
"(batch_size, num_directions, hidden_size) is dynamic. "
"\n`X` input onnx shape {seq_length, batch_size, input_size} is ",
ng_inputs.at(0).get_partial_shape(),
"\n`R` input onnx shape {num_directions, 4*hidden_size, "
"hidden_size} is ",
ng_inputs.at(2).get_partial_shape());
m_input_map[LSTMInput::LSTM_INPUT_INIT_C] =
default_opset::Constant::create(
m_input_map[LSTMInput::LSTM_INPUT_X].get_element_type(),
Shape{m_dim_map[LSTMInputDimension::BATCH_SIZE],
m_dim_map[LSTMInputDimension::NUM_DIRECTIONS],
m_dim_map[LSTMInputDimension::HIDDEN_SIZE]},
std::vector<float>(
m_dim_map[LSTMInputDimension::BATCH_SIZE] *
m_dim_map[LSTMInputDimension::NUM_DIRECTIONS] *
m_dim_map[LSTMInputDimension::HIDDEN_SIZE],
0.f));
} }
// The weight tensor for peepholes. Shape [num_directions, 3*hidde_size] // `P` - The weight tensor for peepholes.
// Peepholes input is not supported by OpenVino // Peepholes input is not supported by OpenVino
if (ng_inputs.size() > 7 && !ngraph::op::is_null(ng_inputs.at(7))) if (ng_inputs.size() > 7 && !ngraph::op::is_null(ng_inputs.at(7)))
{ {
@ -176,8 +297,9 @@ namespace ngraph
} }
} }
Output<ngraph::Node>& at(const LSTMInput& key) { return m_map.at(key); } Output<ngraph::Node>& at(const LSTMInput& key) { return m_input_map.at(key); }
container_type m_map; std::map<LSTMInput, Output<ngraph::Node>> m_input_map;
std::map<LSTMInputDimension, size_t> m_dim_map;
}; };
// ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ATTRIBUTES PARSING ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ // ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ATTRIBUTES PARSING ~~~~~~~~~~~~~~~~~~~~~~~~~~~~

1
ngraph/python/tests/__init__.py
View File

@ -235,3 +235,4 @@ xfail_issue_39663 = xfail_test(reason="RuntimeError: Unsupported primitive of ty
xfail_issue_41815 = xfail_test(reason="RuntimeError: Unsupported dynamic ops: v5::NonMaxSuppression casted " xfail_issue_41815 = xfail_test(reason="RuntimeError: Unsupported dynamic ops: v5::NonMaxSuppression casted "
"(yolo_evaluation_layer_1/concat_6:0_btc[0]:f32{1,2535,4},") "(yolo_evaluation_layer_1/concat_6:0_btc[0]:f32{1,2535,4},")
xfail_issue_41894 = xfail_test(reason="CPU plugin elementwise computation missmatch") xfail_issue_41894 = xfail_test(reason="CPU plugin elementwise computation missmatch")
xfail_issue_42818 = xfail_test(reason="AssertionError: This model has no test data")

8
ngraph/python/tests/test_onnx/test_zoo_models.py
View File

@ -38,7 +38,8 @@ from tests import (
xfail_issue_39669, xfail_issue_39669,
xfail_issue_38726, xfail_issue_38726,
xfail_issue_40686, xfail_issue_40686,
xfail_issue_42779) xfail_issue_42779,
xfail_issue_42818)
MODELS_ROOT_DIR = tests.MODEL_ZOO_DIR MODELS_ROOT_DIR = tests.MODEL_ZOO_DIR
@ -123,7 +124,6 @@ if len(zoo_models) > 0:
(xfail_issue_42297, "test_MSFT_opset10_mlperf_ssd_mobilenet_300_ssd_mobilenet_v1_coco_2018_01_28_cpu"), (xfail_issue_42297, "test_MSFT_opset10_mlperf_ssd_mobilenet_300_ssd_mobilenet_v1_coco_2018_01_28_cpu"),
(xfail_issue_41814, "test_MSFT_opset10_mlperf_ssd_resnet34_1200_ssd_resnet34_mAP_20.2_cpu"), (xfail_issue_41814, "test_MSFT_opset10_mlperf_ssd_resnet34_1200_ssd_resnet34_mAP_20.2_cpu"),
(xfail_issue_37957, "test_MSFT_opset10_mask_rcnn_keras_mask_rcnn_keras_cpu"), (xfail_issue_37957, "test_MSFT_opset10_mask_rcnn_keras_mask_rcnn_keras_cpu"),
(xfail_issue_36465, "test_MSFT_opset9_LSTM_Seq_lens_unpacked_model_cpu"),
] ]
for test_case in import_xfail_list: for test_case in import_xfail_list:
xfail, test_name = test_case xfail, test_name = test_case
@ -182,7 +182,9 @@ if len(zoo_models) > 0:
(xfail_issue_34323, "test_MSFT_opset10_BERT_Squad_bertsquad10_cpu"), (xfail_issue_34323, "test_MSFT_opset10_BERT_Squad_bertsquad10_cpu"),
(xfail_issue_41815, "test_MSFT_opset11_tinyyolov3_yolov3_tiny_cpu"), (xfail_issue_41815, "test_MSFT_opset11_tinyyolov3_yolov3_tiny_cpu"),
(xfail_issue_41815, "test_MSFT_opset10_yolov3_yolov3_cpu") (xfail_issue_41815, "test_MSFT_opset10_yolov3_yolov3_cpu"),
(xfail_issue_42818, "test_MSFT_opset9_LSTM_Seq_lens_unpacked_model_cpu"),
] ]
for test_case in import_xfail_list + execution_xfail_list: for test_case in import_xfail_list + execution_xfail_list:
xfail, test_name = test_case xfail, test_name = test_case

278
ngraph/test/models/onnx/dynamic_shapes/lstm_dyn_batch_seq.prototxt Normal file
View File

@ -0,0 +1,278 @@
ir_version: 7
producer_name: "onnx-importer-test"
graph {
node {
output: "W"
op_type: "Constant"
attribute {
name: "value"
t {
dims: 1
dims: 12
dims: 1
data_type: 1
float_data: 0.31403765082359314
float_data: -0.16793324053287506
float_data: 1.3882579803466797
float_data: -0.690295398235321
float_data: -0.39940449595451355
float_data: -0.7833511233329773
float_data: -0.30992957949638367
float_data: 0.35575729608535767
float_data: -0.46826308965682983
float_data: 1.1741459369659424
float_data: -2.4147889614105225
float_data: -0.42783254384994507
name: "const_tensor_W"
}
type: TENSOR
}
}
node {
output: "R"
op_type: "Constant"
attribute {
name: "value"
t {
dims: 1
dims: 12
dims: 3
data_type: 1
float_data: 0.8490582704544067
float_data: 0.45121243596076965
float_data: -1.179901361465454
float_data: 0.13536448776721954
float_data: 0.813286542892456
float_data: 0.6017516255378723
float_data: 0.4847572445869446
float_data: -1.2136037349700928
float_data: 0.16383321583271027
float_data: 1.5106260776519775
float_data: 1.1177502870559692
float_data: 0.2358246147632599
float_data: 0.8490582704544067
float_data: 0.45121243596076965
float_data: -1.179901361465454
float_data: 0.13536448776721954
float_data: 0.813286542892456
float_data: 0.6017516255378723
float_data: 0.4847572445869446
float_data: -1.2136037349700928
float_data: 0.16383321583271027
float_data: 1.5106260776519775
float_data: 1.1177502870559692
float_data: 0.2358246147632599
float_data: 0.8490582704544067
float_data: 0.45121243596076965
float_data: -1.179901361465454
float_data: 0.13536448776721954
float_data: 0.813286542892456
float_data: 0.6017516255378723
float_data: 0.4847572445869446
float_data: -1.2136037349700928
float_data: 0.16383321583271027
float_data: 1.5106260776519775
float_data: 1.1177502870559692
float_data: 0.2358246147632599
name: "const_tensor"
}
type: TENSOR
}
}
node {
output: "B"
op_type: "Constant"
attribute {
name: "value"
t {
dims: 1
dims: 24
data_type: 1
float_data: 0.53367018699646
float_data: 1.6593654155731201
float_data: -1.1500109434127808
float_data: 0.0034221699461340904
float_data: 0.7993710041046143
float_data: 0.43780383467674255
float_data: -0.5508262515068054
float_data: 1.0774186849594116
float_data: -0.606513500213623
float_data: 0.6434063911437988
float_data: -1.5693753957748413
float_data: 1.4923384189605713
float_data: 1.1554348468780518
float_data: -1.328158974647522
float_data: 0.24995532631874084
float_data: 0.15112681686878204
float_data: -0.3469875752925873
float_data: -0.100888192653656
float_data: -0.2931624948978424
float_data: -0.4731961488723755
float_data: 0.6616785526275635
float_data: -1.1646721363067627
float_data: -0.09588219225406647
float_data: 0.5212928056716919
name: "const_tensor"
}
type: TENSOR
}
}
node {
input: "X"
input: "W"
input: "R"
input: "B"
input: "sequence_lens"
input: "initial_h"
input: "initial_c"
output: "Y"
output: "Y_h"
output: "Y_c"
op_type: "LSTM"
attribute {
name: "direction"
s: "forward"
type: STRING
}
attribute {
name: "hidden_size"
i: 3
type: INT
}
}
name: "test-model-lstm"
input {
name: "X"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: -1
}
dim {
dim_value: -1
}
dim {
dim_value: 1
}
}
}
}
}
input {
name: "sequence_lens"
type {
tensor_type {
elem_type: 6
shape {
dim {
dim_value: -1
}
}
}
}
}
input {
name: "initial_h"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: 1
}
dim {
dim_value: -1
}
dim {
dim_value: 3
}
}
}
}
}
input {
name: "initial_c"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: 1
}
dim {
dim_value: -1
}
dim {
dim_value: 3
}
}
}
}
}
output {
name: "Y"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: -1
}
dim {
dim_value: 1
}
dim {
dim_value: -1
}
dim {
dim_value: 3
}
}
}
}
}
output {
name: "Y_h"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: 1
}
dim {
dim_value: -1
}
dim {
dim_value: 3
}
}
}
}
}
output {
name: "Y_c"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: 1
}
dim {
dim_value: -1
}
dim {
dim_value: 3
}
}
}
}
}
}
opset_import {
domain: ""
version: 12
}

21
ngraph/test/onnx/onnx_import_rnn.in.cpp
View File

@ -491,6 +491,27 @@ NGRAPH_TEST(${BACKEND_NAME}, onnx_model_lstm_mixed_seq_reverse)
test_case.run(DEFAULT_FLOAT_TOLERANCE_BITS + 1); test_case.run(DEFAULT_FLOAT_TOLERANCE_BITS + 1);
} }
NGRAPH_TEST(${BACKEND_NAME}, onnx_model_import_only_lstm_dynamic_batch_seq_all_inputs)
{
auto function = onnx_import::import_onnx_model(
file_util::path_join(SERIALIZED_ZOO, "onnx/dynamic_shapes/lstm_dyn_batch_seq.prototxt"));
auto batch_size = Dimension::dynamic();
auto seq_length = Dimension::dynamic();
int64_t hidden_size = 3;
int64_t num_directions = 1;
auto Y_expected_output = PartialShape{batch_size, num_directions, seq_length, hidden_size};
auto Y_h_expected_output = PartialShape{num_directions, batch_size, hidden_size};
auto Y_c_expected_output = PartialShape{num_directions, batch_size, hidden_size};
EXPECT_EQ(function->get_output_size(), 3);
EXPECT_EQ(function->get_output_partial_shape(0), Y_expected_output);
EXPECT_EQ(function->get_output_partial_shape(1), Y_h_expected_output);
EXPECT_EQ(function->get_output_partial_shape(2), Y_c_expected_output);
EXPECT_EQ(count_ops_of_type<op::v5::LSTMSequence>(function), 1);
}
// RNNLikeSequenceOp test fixture for test setup reuse // RNNLikeSequenceOp test fixture for test setup reuse
class GRUSequenceOp : public testing::Test class GRUSequenceOp : public testing::Test
{ {