Is matmul operation automatically considered?

[GostInShell]

Is a torch.matmul operation implemented in a forward layer automatically considered?

[GostInShell]

The matmul implemented here

pytorch-OpCounter/thop/vision/counter.py

Line 67 in 509fb7e

 def counter_matmul(input_size, output_size): 

seems to be used in

pytorch-OpCounter/thop/vision/onnx_counter.py

Line 19 in d74140c

 def onnx_counter_matmul(diction, node): 

Does this indicate the FLOPs of matmul will be considered when using ONNX model rather than a pytorch one?

[Hao Kang]

Yes it does.
ONNX model counter depends on operators, while PyTorch model counter depends on layers. You will get similar results when using both models(if we have implemented related operators and layers).
Thop pytorch model counter will not count matmul, but it will be considered in the case that matmul is used in the layer(such as convolution layers).

[GostInShell]

Thanks a lot! That perfectly solved my confusion!