driver-action-recognition-adas-0002-decoder model conversion error

[ooe1123]

OS: Ubuntu 20.04 OS Architecture: x86_64 Version of OpenVINO: 2021.4 Version of ONNX: 1.10.1 Download URL for OpenVINO IR (.bin/.xml) model: https://storage.openvinotoolkit.org/repositories/open_model_zoo/2021.4/models_bin/3/driver-action-recognition-adas-0002/driver-action-recognition-adas-0002-decoder/FP32/

I want to convert the open model zoo, driver-action-recognition-adas-0002-decoder into saved_model format.

openvino2tensorflow --model_path driver-action-recognition-adas-0002-decoder.xml --output_saved_model

But I recieve error.

ERROR: list index out of range
ERROR: model_path  : driver-action-recognition-adas-0002-decoder.xml
ERROR: weights_path: driver-action-recognition-adas-0002-decoder.bin
ERROR: layer_id    : 125
ERROR: input_layer0 layer_id=123: KerasTensor(type_spec=TensorSpec(shape=(1, 512, 16), dtype=tf.float32, name=None), name='tf.compat.v1.transpose_1/transpose:0', description="created by layer 'tf.compat.v1.transpose_1'")
ERROR: input_layer1 layer_id=124: Const(ndarray).shape  (1024, 512, 1)
array([[
  ...
  ]], dtype=float32)
ERROR: The trace log is below.
Traceback (most recent call last):
  File "/home/ooe/env1/bin/openvino2tensorflow", line 599, in convert
    kernel_size = [int(port1[2]), int(port1[3])]
IndexError: list index out of range

How can i solve the problem?

[PINTO0309]

Fixes. https://github.com/PINTO0309/openvino2tensorflow/releases/tag/v1.21.1

[ooe1123]

Thank you for updating. But next I get the following error.

====================================================================================
layer_type: Const
layer_id: 124
tf_layers_dict: (1024, 512, 1)
====================================================================================
ERROR: Depth of input (16) is not a multiple of input depth of filter (512) for '{{node tf.nn.conv1d/conv1d}} = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], explicit_paddings=[], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](tf.nn.conv1d/conv1d/ExpandDims, tf.nn.conv1d/conv1d/ExpandDims_1)' with input shapes: [1,1,512,16], [1,1,512,1024].
ERROR: model_path  : driver-action-recognition-adas-0002-decoder.xml
ERROR: weights_path: driver-action-recognition-adas-0002-decoder.bin
ERROR: layer_id    : 125
ERROR: input_layer0 layer_id=123: KerasTensor(type_spec=TensorSpec(shape=(1, 512, 16), dtype=tf.float32, name=None), name='tf.compat.v1.transpose_1/transpose:0', description="created by layer 'tf.compat.v1.transpose_1'")
ERROR: input_layer1 layer_id=124: Const(ndarray).shape  (1024, 512, 1)
array([[
        ...
        ]], dtype=float32)
ERROR: The trace log is below.
Traceback (most recent call last):
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py", line 206, in wrapper
    return target(*args, **kwargs)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/util/deprecation.py", line 617, in new_func
    return func(*args, **kwargs)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/util/deprecation.py", line 617, in new_func
    return func(*args, **kwargs)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/ops/nn_ops.py", line 2003, in conv1d
    result = gen_nn_ops.conv2d(
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 936, in conv2d
    return conv2d_eager_fallback(
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 1019, in conv2d_eager_fallback
    _attr_T, _inputs_T = _execute.args_to_matching_eager([input, filter], ctx, [_dtypes.half, _dtypes.bfloat16, _dtypes.float32, _dtypes.float64, _dtypes.int32, ])
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/eager/execute.py", line 280, in args_to_matching_eager
    ret = [ops.convert_to_tensor(t, dtype, ctx=ctx) for t in l]
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/eager/execute.py", line 280, in <listcomp>
    ret = [ops.convert_to_tensor(t, dtype, ctx=ctx) for t in l]
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/profiler/trace.py", line 163, in wrapped
    return func(*args, **kwargs)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/framework/ops.py", line 1566, in convert_to_tensor
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 346, in _constant_tensor_conversion_function
    return constant(v, dtype=dtype, name=name)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 271, in constant
    return _constant_impl(value, dtype, shape, name, verify_shape=False,
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 283, in _constant_impl
    return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 308, in _constant_eager_impl
    t = convert_to_eager_tensor(value, ctx, dtype)
  File "/home/ooe/env1/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 106, in convert_to_eager_tensor
    return ops.EagerTensor(value, ctx.device_name, dtype)
  File "/home/ooe/env1/lib/python3.8/site-packages/keras/engine/keras_tensor.py", line 244, in __array__
    raise TypeError(
TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.

[PINTO0309]

https://github.com/PINTO0309/openvino2tensorflow/tree/v1.21.1#6-7-replace-weights-or-constant-values-in-const-op-and-add-transpose-or-reshape-or-cast-just-beforeafter-the-operation-specified-by-layer_id

https://github.com/PINTO0309/PINTO_model_zoo/tree/main/154_driver-action-recognition-adas-0002-encoder https://github.com/PINTO0309/PINTO_model_zoo/tree/main/155_driver-action-recognition-adas-0002-decoder