> ## Description > I found out that the required weight count is twice as in the onnx model, but it's not clear how to fix this error > >...
> ## Description > I found out that the required weight count is twice as in the onnx model, but it's not clear how to fix this error > >...
> error node:  [08/17/2022-17:06:41] [TRT] [E] Conv_1840: count of 1474560 weights in kernel, but kernel dimensions (3,3) with 320 input channels, 512 output channels and 2 groups were specified....
> Failed to parse the ONNX file: end2end.onnx > ERROR: Failed to parse the ONNX file. i have the same problem, how to solve?
later. now do you have method to > FYI, we will have scatterElements plugin with reduction support in 10.0. when?
@demuxin do you have resolve this problem
> Hi, could you provide details on what you are trying to achieve, as well as an example that reproduces the behavior you are getting? Also, could this be related...
in unfoldNd function failed ，the error is Unsupported: ONNX export of convolution for kernel of unknown shape
i onnx convert to tensorrt success，but the rusult is wrong,i find in output.scatter_add_(2, idx[:, :, k, :], input[:, :, k, :]) scatter_add_ not work in tensorRT