Open niuniu1988 opened 4 years ago
Hi, Any resolution?
I have same issue, prediction is always the same. Any one solve this?
same issue I faced. It seems the tensor/scalar values are treated as constant at some layers. need to implement converters for those layers.
do you have some resolutions?
net forward code
convert pytorch to trt
net = Classifier().eval().cuda() net.load_state_dict(torch.load(model_path))
x = torch.ones(batch_size, 3, 224, 224).cuda() model_trt = torch2trt(net, [x])
show error
Warning: Encountered known unsupported method torch.bmm [TensorRT] ERROR: INVALID_ARGUMENT: Cannot find binding of given name: input_0
when use the model_trt, the prediction is always the same, no matter what is the label of the image. how to solve this problem?