niuwagege

in backward_g()，call self.netd() to get features. `self.err_g_adv = self.l_adv(self.netd(self.input)[1], self.netd(self.fake)[1])` why not use self.feat_real and self.feat_fake that you get from forward_d() directly

[8] Assertion failed: nbSpatialDims == kernelWeights.shape.nbDims - 2

3

## Description converting onnx to tensorrt, occur [[8] Assertion failed: nbSpatialDims == kernelWeights.shape.nbDims - 2]  command: ./trtexec --onnx=test.onnx --saveEngine=test.trt --explicitBatch --workspace=4096 ## Environment **TensorRT Version**: 7.2.1.6 **ONNX-TensorRT Version /...