Getting error while converting tensorrt model to Onnx.
Seems to be numpy.product function is now numpy.prod with numpy 2.0
~# python3 yolo_to_onnx.py -m yolov7-320
Parsing DarkNet cfg file...
Building ONNX graph...
Traceback (most recent call last):
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 1065, in
main()
~~~~^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 1050, in main
yolo_model_def = builder.build_onnx_graph(
layer_configs=layer_configs,
weights_file_path=weights_file_path,
verbose=True)
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 584, in build_onnx_graph
initializer_layer, inputs_layer = weight_loader.load_conv_weights(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
params)
^^^^^^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 441, in load_conv_weights
bias_init, bias_input = self._create_param_tensors(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
conv_params, 'bn', 'bias')
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 486, in _create_param_tensors
param_name, param_data, param_data_shape = self._load_one_param_type(
~~~~~~~~~~~~~~~~~~~~~~~~~^
conv_params, param_category, suffix)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 513, in _load_one_param_type
param_size = np.product(np.array(param_shape))
^^^^^^^^^^
File "/usr/lib/python3/dist-packages/numpy/init.py", line 414, in getattr
raise AttributeError("module {!r} has no attribute "
"{!r}".format(name, attr))
AttributeError: module 'numpy' has no attribute 'product
Getting error while converting tensorrt model to Onnx.
Seems to be numpy.product function is now numpy.prod with numpy 2.0
~# python3 yolo_to_onnx.py -m yolov7-320
Parsing DarkNet cfg file...
Building ONNX graph...
Traceback (most recent call last):
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 1065, in
main()
~~~~^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 1050, in main
yolo_model_def = builder.build_onnx_graph(
layer_configs=layer_configs,
weights_file_path=weights_file_path,
verbose=True)
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 584, in build_onnx_graph
initializer_layer, inputs_layer = weight_loader.load_conv_weights(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
params)
^^^^^^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 441, in load_conv_weights
bias_init, bias_input = self._create_param_tensors(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
conv_params, 'bn', 'bias')
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 486, in _create_param_tensors
param_name, param_data, param_data_shape = self._load_one_param_type(
~~~~~~~~~~~~~~~~~~~~~~~~~^
conv_params, param_category, suffix)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/tensorrt_demos/yolo/yolo_to_onnx.py", line 513, in _load_one_param_type
param_size = np.product(np.array(param_shape))
^^^^^^^^^^
File "/usr/lib/python3/dist-packages/numpy/init.py", line 414, in getattr
raise AttributeError("module {!r} has no attribute "
"{!r}".format(name, attr))
AttributeError: module 'numpy' has no attribute 'product