search

onnx / onnx-tensorflow

Tensorflow Backend for ONNX
Other
1.26k stars 298 forks source link

Error export onnx model to tensorflow #1036

Open ehsanrahnama opened 2 years ago

ehsanrahnama commented 2 years ago

I have a quantize onnx model and also I want to export to tf and then export to tflite(tensorflow-lite). But unfortunately I face this error. Could you please help me to convert my model?

Traceback (most recent call last): File "onnx_export_tf.py", line 25, in tf_rep.export_graph(tf_model_path) File "/home/server/w/tmp/onnx-tensorflow/onnx_tf/backend_rep.py", line 143, in export_graph signatures=self.tf_module.call.get_concrete_function( File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 1264, in get_concrete_function concrete = self._get_concrete_function_garbage_collected(*args, kwargs) File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 1244, in _get_concrete_function_garbage_collected self._initialize(args, kwargs, add_initializers_to=initializers) File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 785, in _initialize self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 2983, in _get_concrete_function_internal_garbage_collected graphfunction, = self._maybe_define_function(args, kwargs) File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3292, in _maybe_define_function graph_function = self._create_graph_function(args, kwargs) File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3130, in _create_graph_function func_graph_module.func_graph_from_py_func( File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1161, in func_graph_from_py_func func_outputs = python_func(*func_args, *func_kwargs) File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 677, in wrapped_fn out = weak_wrapped_fn().wrapped(args, kwds) File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3831, in bound_method_wrapper return wrapped_fn(*args, **kwargs) File "/home/server/miniconda3/envs/myenv2/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1147, in autograph_handler raise e.ag_error_metadata.to_exception(e) ValueError: in user code:

File "/home/server/w/tmp/onnx-tensorflow/onnx_tf/backend_tf_module.py", line 99, in __call__  *
    output_ops = self.backend._onnx_node_to_tensorflow_op(onnx_node,
File "/home/server/w/tmp/onnx-tensorflow/onnx_tf/backend.py", line 347, in _onnx_node_to_tensorflow_op  *
    return handler.handle(node, tensor_dict=tensor_dict, strict=strict)
File "/home/server/w/tmp/onnx-tensorflow/onnx_tf/handlers/handler.py", line 59, in handle  *
    return ver_handle(node, **kwargs)
File "/home/server/w/tmp/onnx-tensorflow/onnx_tf/handlers/backend/q_linear_conv.py", line 69, in version_10  *
    B = tf.round(B / B_scale)

ValueError: Dimensions must be equal, but are 32 and 12 for '{{node truediv}} = RealDiv[T=DT_FLOAT](Cast_787, mul_385)' with input shapes: [32], [12].