ResNet32 Architecture

1

Hi, I tried to replace ResNet50 architecture with ResNet32 in one model to find the accuracy of the model. But it generated the following error. Any help in this regard would be appreciated.

size mismatch, m1: [256 x 10], m2: [512 x 512] at /opt/conda/conda-bld/pytorch_1565272271120/work/aten/src/THC/generic/THCTensorMathBlas.cu:273

2

What is your input size and other sizes? An easy way to debug your problem is to add print(tensor.shape) statements in the model.