Reproducing mini_imagenet experiments

[Yiqin-Luo]

File "/data/Code/Incremental_learning/PCR-main/models/resnet.py", line 85, in forward
cos_dist = torch.mm(x_normalized,weight_normalized.transpose(0,1))
RuntimeError: mat1 and mat2 shapes cannot be multiplied (30x640 and 160x100)

In the case of the PCR model, encountering error prompts occurs when attempting to execute the code directly with the mini_imagenet dataset. May I request specific details regarding the configuration of the mini_imagenet dataset within the model? This includes information such as the setup_elements.py file. Your assistance in this matter is greatly appreciated.