--input format update in MO docs (#14272)

* Updated input param in docs. * Updated input param in docs.
2022-11-28 20:20:13 +04:00
1 parent 9d954c7920
commit af49e51b54
@@ -38,7 +38,7 @@ mo --input_model ocr.onnx --input data,seq_len --input_shape [3,150,200,1],[3]
 Alternatively, specify input shapes, using the `--input` parameter as follows:

 ```sh
-mo --input_model ocr.onnx --input data[3 150 200 1],seq_len[3]
+mo --input_model ocr.onnx --input data[3,150,200,1],seq_len[3]
 ```

 The `--input_shape` parameter allows overriding original input shapes to ones compatible with a given model.
@@ -71,7 +71,7 @@ It is worth noting that the `--input_shape` parameter does not affect reshapeabi
 For example, launch Model Optimizer for the ONNX OCR model using `--static_shape`:

 ```sh
-mo --input_model ocr.onnx --input data[3 150 200 1],seq_len[3] --static_shape
+mo --input_model ocr.onnx --input data[3,150,200,1],seq_len[3] --static_shape
 ```

 ## Additional Resources
@@ -52,7 +52,7 @@ The script generates ONNX model file `bert-ner.onnx`.
 ## Converting an ONNX BERT-NER model to IR

 ```bash
-mo --input_model bert-ner.onnx --input "input_mask[1 128],segment_ids[1 128],input_ids[1 128]"
+mo --input_model bert-ner.onnx --input "input_mask[1,128],segment_ids[1,128],input_ids[1,128]"
 ```

 where `1` is `batch_size` and `128` is `sequence_length`.
@@ -99,8 +99,8 @@ After completing this step, the files `rnnt_encoder.onnx`, `rnnt_prediction.onnx
 **Step 6**. Run the conversion commands:

 ```sh
-mo --input_model rnnt_encoder.onnx --input "input[157 1 240],feature_length->157"
-mo --input_model rnnt_prediction.onnx --input "symbol[1 1],hidden_in_1[2 1 320],hidden_in_2[2 1 320]"
-mo --input_model rnnt_joint.onnx --input "0[1 1 1024],1[1 1 320]"
+mo --input_model rnnt_encoder.onnx --input "input[157,1,240],feature_length->157"
+mo --input_model rnnt_prediction.onnx --input "symbol[1,1],hidden_in_1[2,1,320],hidden_in_2[2,1,320]"
+mo --input_model rnnt_joint.onnx --input "0[1,1,1024],1[1,1,320]"
 ```
 > **NOTE**: The hardcoded value for sequence length = 157 was taken from the MLCommons, but conversion to IR preserves network [reshapeability](@ref openvino_docs_OV_UG_ShapeInference). Therefore, input shapes can be changed manually to any value during either conversion or inference.
@@ -24,7 +24,7 @@ The resized image is sent to the convolution neural network (CNN). Because Model
 ```sh
 mo \
 --input_model=model/path/frozen_graph.pb \
--input="map/TensorArrayStack/TensorArrayGatherV3:0[1 32 86 1]" \
+--input="map/TensorArrayStack/TensorArrayGatherV3:0[1,32,86,1]" \
 --output "transpose_1,transpose_2" \
 --output_dir path/to/ir/
 ```
@@ -112,7 +112,7 @@ Run Model Optimizer with the following command line parameters to generate resha
 ```sh
 mo \
 --input_model inference_graph.pb \
--input "IteratorGetNext:0{i32}[1 128],IteratorGetNext:1{i32}[1 128],IteratorGetNext:4{i32}[1 128]"
+--input "IteratorGetNext:0{i32}[1,128],IteratorGetNext:1{i32}[1,128],IteratorGetNext:4{i32}[1,128]"
 ```
 For other applicable parameters, refer to the [Convert Model from TensorFlow](../Convert_Model_From_TensorFlow.md) guide.

@@ -70,7 +70,7 @@ To generate the IR, run Model Optimizer with the following parameters:
 ```sh
 mo                             \
 --input_model output_graph.pb  \
--input "input_lengths->[16],input_node[1 16 19 26],previous_state_h[1 2048],previous_state_c[1 2048]"   \
+--input "input_lengths->[16],input_node[1,16,19,26],previous_state_h[1,2048],previous_state_c[1,2048]"   \
 --output "cudnn_lstm/rnn/multi_rnn_cell/cell_0/cudnn_compatible_lstm_cell/GatherNd_1,cudnn_lstm/rnn/multi_rnn_cell/cell_0/cudnn_compatible_lstm_cell/GatherNd,logits"
 ```

@@ -198,7 +198,7 @@ tgt_vocab_size -= 1
 ```sh
 mo
 --input_model /path/to/dump/model/frozen_GNMT_inference_graph.pb
--input "IteratorGetNext:1{i32}[1],IteratorGetNext:0{i32}[1 50],dynamic_seq2seq/hash_table_Lookup_1:0[1]->[2],dynamic_seq2seq/hash_table_Lookup:0[1]->[1]"
+--input "IteratorGetNext:1{i32}[1],IteratorGetNext:0{i32}[1,50],dynamic_seq2seq/hash_table_Lookup_1:0[1]->[2],dynamic_seq2seq/hash_table_Lookup:0[1]->[1]"
 --output dynamic_seq2seq/decoder/decoder/GatherTree
 --output_dir /path/to/output/IR/
 ```
@@ -7,7 +7,7 @@ To convert this model to the TensorFlow format, follow the [Reproduce Keras to T

 After converting the model to TensorFlow format, run the Model Optimizer command below:
 ```sh
-mo --input "input_1[1 1333 1333 3]" --input_model retinanet_resnet50_coco_best_v2.1.0.pb --transformations_config front/tf/retinanet.json
+mo --input "input_1[1,1333,1333,3]" --input_model retinanet_resnet50_coco_best_v2.1.0.pb --transformations_config front/tf/retinanet.json
 ```

 Where `transformations_config` command-line parameter specifies the configuration json file containing model conversion hints for the Model Optimizer.
@@ -99,30 +99,30 @@ Use the following command line to convert the saved model file with the checkpoi
         IteratorGetNext:2[2],
         IteratorGetNext:4[2],
         IteratorGetNext:7[2],
-         linear/linear_model/linear_model/linear_model/education/to_sparse_input/indices:0[10 2]{i64},
+         linear/linear_model/linear_model/linear_model/education/to_sparse_input/indices:0[10,2]{i64},
         linear/linear_model/linear_model/linear_model/education/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         linear/linear_model/linear_model/linear_model/education/to_sparse_input/dense_shape:0[2]{i64}->[2 50],
-         linear/linear_model/linear_model/linear_model/marital_status/to_sparse_input/indices:0[10 2]{i64},
+         linear/linear_model/linear_model/linear_model/education/to_sparse_input/dense_shape:0[2]{i64}->[2,50],
+         linear/linear_model/linear_model/linear_model/marital_status/to_sparse_input/indices:0[10,2]{i64},
         linear/linear_model/linear_model/linear_model/marital_status/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         linear/linear_model/linear_model/linear_model/marital_status/to_sparse_input/dense_shape:0[2]{i64}->[2 50],
-         linear/l inear_model/linear_model/linear_model/relationship/to_sparse_input/indices:0[10 2]{i64},
+         linear/linear_model/linear_model/linear_model/marital_status/to_sparse_input/dense_shape:0[2]{i64}->[2,50],
+         linear/linear_model/linear_model/linear_model/relationship/to_sparse_input/indices:0[10,2]{i64},
         linear/linear_model/linear_model/linear_model/relationship/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         linear/linear_model/linear_model/linear_model/relationship/to_sparse_input/dense_shape:0[2]{i64}->[2 50],
-         linear/linear_model/linear_model/linear_model/workclass/to_sparse_input/indices:0[10 2]{i64},
+         linear/linear_model/linear_model/linear_model/relationship/to_sparse_input/dense_shape:0[2]{i64}->[2,50],
+         linear/linear_model/linear_model/linear_model/workclass/to_sparse_input/indices:0[10,2]{i64},
         linear/linear_model/linear_model/linear_model/workclass/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         linear/linear_model/linear_model/linear_model/workclass/to_sparse_input/dense_shape:0[2]{i64}->[2 50],
-         dnn/input_from_feature_columns/input_layer/education_indicator/to_sparse_input/indices:0[10 2]{i64},
+         linear/linear_model/linear_model/linear_model/workclass/to_sparse_input/dense_shape:0[2]{i64}->[2,50],
+         dnn/input_from_feature_columns/input_layer/education_indicator/to_sparse_input/indices:0[10,2]{i64},
         dnn/input_from_feature_columns/input_layer/education_indicator/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         dnn/input_from_feature_columns/input_layer/education_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2 50],
-         dnn/input_from_feature_columns/input_layer/marital_status_indicator/to_sparse_input/indices:0[10 2]{i64},
+         dnn/input_from_feature_columns/input_layer/education_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2,50],
+         dnn/input_from_feature_columns/input_layer/marital_status_indicator/to_sparse_input/indices:0[10,2]{i64},
         dnn/input_from_feature_columns/input_layer/marital_status_indicator/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         dnn/input_from_feature_columns/input_layer/marital_status_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2 50],
-         dnn/input_from_feature_columns/input_layer/relationship_indicator/to_sparse_input/indices:0[10 2]{i64},
+         dnn/input_from_feature_columns/input_layer/marital_status_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2,50],
+         dnn/input_from_feature_columns/input_layer/relationship_indicator/to_sparse_input/indices:0[10,2]{i64},
         dnn/input_from_feature_columns/input_layer/relationship_indicator/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         dnn/input_from_feature_columns/input_layer/relationship_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2 50],
-         dnn/input_from_feature_columns/input_layer/workclass_indicator/to_sparse_input/indices:0[10 2]{i64},
+         dnn/input_from_feature_columns/input_layer/relationship_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2,50],
+         dnn/input_from_feature_columns/input_layer/workclass_indicator/to_sparse_input/indices:0[10,2]{i64},
         dnn/input_from_feature_columns/input_layer/workclass_indicator/hash_table_Lookup/LookupTableFindV2:0[10]{i64},
-         dnn/input_from_feature_columns/input_layer/workclass_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2 50]"
+         dnn/input_from_feature_columns/input_layer/workclass_indicator/to_sparse_input/dense_shape:0[2]{i64}->[2,50]"
 --output head/predictions/probabilities
 ```

@@ -184,6 +184,6 @@ To generate the XLNet Intermediate Representation (IR) of the model, run Model O

 ```sh
 mo --input_model path-to-model/model_frozen.pb \
-   --input "input_mask[50 1],input_ids[50 1],seg_ids[50 1]"
+   --input "input_mask[50,1],input_ids[50,1],seg_ids[50,1]"
 ```

@@ -32,7 +32,7 @@ For example, the most common problem of non-reshape-able models is a `Reshape` o
 You can cut-off the hard-coded second input of `Reshape` and fill it in with relaxed values.
 For the following example in the diagram below, the Model Optimizer CLI should read:
 ```sh
-mo --input_model path/to/model --input data[8,3,224,224],1:reshaped[2]->[0 -1]`
+mo --input_model path/to/model --input data[8,3,224,224],1:reshaped[2]->[0,-1]`
 ```

  With `1:reshaped[2]`, it is required to cut the second input (counting from zero, so `1:` means the second input) of the operation named `reshaped` and   replace it with a `Parameter` with shape `[2]`.
@@ -8,6 +8,7 @@ from collections import defaultdict
 from copy import copy

 import numpy as np
+from openvino.runtime import PartialShape, Dimension

 from openvino.tools.mo.front.common.partial_infer.utils import dynamic_dimension_value, shape_array
 from openvino.tools.mo.front.onnx.extractors.utils import get_backend_pad
@@ -18,8 +19,6 @@ from openvino.tools.mo.utils.error import Error
 from openvino.tools.mo.utils.unsupported_ops import UnsupportedOps
 from openvino.tools.mo.utils.utils import refer_to_faq_msg

-from openvino.runtime import PartialShape, Dimension
-

 def restore_edges(graph: Graph, get_edges: callable):
    """
@@ -1024,15 +1023,15 @@ def add_input_ops(graph: Graph, user_defined_inputs: dict, before_infer: bool):
    """
    This function add user defined input operations.
    For cutting without port:
-    Op_1 -> Op_2 -> output, user_defined_inputs = {'Op_2': {'shape':[1, 2]}} =>
+    Op_1 -> Op_2 -> output, user_defined_inputs = {'Op_2': {'shape': PartialShape([1, 2])}} =>
    Op_1,  New_input (op=Parameter, shape=[1, 2]) -> Op_2 -> output

    For cutting with input port:
-    Op_1 -> Op_2 -> output, user_defined_inputs = {'Op_2': {'shape':[1, 2], 'in': 0}} =>
+    Op_1 -> Op_2 -> output, user_defined_inputs = {'Op_2': {'shape':PartialShape([1, 2]), 'in': 0}} =>
    Op_1,  New_input (op=Parameter, shape=[1, 2]) -> Op_2 -> output

    For cutting with output port:
-    Op_1 -> Op_2 -> output, user_defined_inputs = {'Op_2': {'shape':[1, 2], 'out': 0}} =>
+    Op_1 -> Op_2 -> output, user_defined_inputs = {'Op_2': {'shape':PartialShape([1, 2]), 'out': 0}} =>
    Op_1 -> Op_2, New_input (op=Parameter, shape=[1, 2]) -> output

    For case with before_infer=False data nodes are added to this schemes.