Following is my error message:
Traceback (most recent call last):
File “pose_estimation/test_on_single_image_quant_ver.py”, line 119, in
main()
File “pose_estimation/test_on_single_image_quant_ver.py”, line 92, in main
output = quantized_model(input)
File “/usr/lib/python3.8/site-packages/torch/nn/modules/module.py”, line 722, in _call_impl
result = self.forward(*input, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
File “code/torch/models/pose_mobilenet.py”, line 17, in forward
x0 = (self.quant).forward(x, )
x1 = (self.features).forward(x0, )
x2 = (self.conv_transpose_layers).forward(x1, )
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <— HERE
x3 = (self.final_layer).forward(x2, )
return (self.dequant).forward(x3, )
File “code/torch/torch/nn/modules/container/___torch_mangle_4.py”, line 26, in forward
_8 = getattr(self, “8”)
input0 = (_0).forward(input, None, )
input1 = (_1).forward(input0, )
~~~~~~~~~~~ <— HERE
input2 = (_2).forward(input1, )
input3 = (_3).forward(input2, None, )
File “code/torch/torch/nn/modules/container/___torch_mangle_4.py”, line 25, in forward
_7 = getattr(self, “7”)
_8 = getattr(self, “8”)
input0 = (_0).forward(input, None, )
~~~~~~~~~~~ <— HERE
input1 = (_1).forward(input0, )
input2 = (_2).forward(input1, )
File “code/torch/torch/nn/modules/conv.py”, line 22, in forward
output_size: Optional[List[int]]=None) → Tensor:
output_padding = (self)._output_padding(input, output_size, [2, 2], [1, 1], [4, 4], )
_0 = torch.conv_transpose2d(input, self.weight, self.bias, [2, 2], [1, 1], output_padding, 1, [1, 1])
~~~~~~~~~~~~~~~~~~~~~~ <— HERE
return _0
def _output_padding(self: torch.torch.nn.modules.conv.ConvTranspose2d,Traceback of TorchScript, original code (most recent call last):
File “/usr/lib/python3.8/site-packages/torch/nn/modules/container.py”, line 117, in forward
def forward(self, input):
for module in self:
input = module(input)
~~~~~~ <— HERE
return input
File “/usr/lib/python3.8/site-packages/torch/nn/modules/container.py”, line 117, in forward
def forward(self, input):
for module in self:
input = module(input)
~~~~~~ <— HERE
return input
File “/usr/lib/python3.8/site-packages/torch/nn/modules/conv.py”, line 905, in forward
output_padding = self._output_padding(input, output_size, self.stride, self.padding, self.kernel_size)return F.conv_transpose2d( ~~~~~~~~~~~~~~~~~~ <--- HERE input, self.weight, self.bias, self.stride, self.padding, output_padding, self.groups, self.dilation)
RuntimeError: Could not run ‘aten::slow_conv_transpose2d’ with arguments from the ‘QuantizedCPU’ backend. ‘aten::slow_conv_transpose2d’ is only available for these backends: [CPU, CUDA, Autograd, Profiler, Tracer].
I’m new to this, I try to find something like torch.nn.quantized.conv_transpose2d but I can’t find it or is there any other ways?
Thanks in advance