Closed smallccn closed 2 years ago
_params_c is counted by the NodeProfiler which may be wrong sometimes. e.g. the convolution weight is shared among nodes. And if both inputs of Matmul are dynamic tensors, _params_c should be zero but it won't. That's the reason why I deprecated it.
About your problem, I believe it's the case that the convolution weight is shared by multiple nodes. You can check the console logs for "Weight Sharing is detected".
https://github.com/ThanatosShinji/onnx-tool/blob/b6f2ef777d89dd4e294a6e29a16b29fb74fb5ca4/onnx_tool/__init__.py#L192-L208
Dear sir,
About those codes, I have some questions, after call node_profile, the return value
_params_c
is not used. And_params
is used as the params of this node, for some nets(ex. Retinanet), this will lead to some Conv's params is0
.When I use
_params_c
to replace_params
, it seems that I can get a correct result.So could you please help to share some ideas about this? Thanks.