pytorch-classification

pytorch-classification copied to clipboard

RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

1


happy20200

Error(s) in loading state_dict for DataParallel:

11

When I download the pre_trained model and resume it. there is an error. model.load_state_dict(checkpoint['state_dict']) It seems that the name are not matched.(e.g. "module.features.0.weight" v.s. "features.module.0.weight") How could I solve it...

cosmolu

Error loading pretrained model weights

1

When I try resuming from the pretrained model weight I get an error This is what I am running: `python cifar.py -a preresnet --depth 110 --epochs 3 --schedule 81 122...

raghav1810

changed view to reshape in line 16 to handle non contiguous tensors.

RajArPatra

We use your checkpoints but I derive the best results at step 1. Is It the best model parameters or the pretrained models. I'm not sure about it and hope...

qingxu-thu

dalveasy

The ResNeXt-29 (16x64) trained model on CIFAR10 in OneDrive seems to be inconsistent with the result listed in the table. Will it be possible to upload the correct version? ![Screenshot...

Xiuyu-Li

yanghu819

I am on a tight deadline. Could you tell me about how long ImageNet takes to train?

slerman12

About tiny imagenet training problem

1

I have modified the imagenet.py by adding the lines after the "create model" codes: num_ftrs = model.fc.in_features model.fc = nn.Linear(num_ftrs,200) changing the net to train on tiny imagenet. But it...

zorrocai