pytorch_resnet_cifar10
pytorch_resnet_cifar10 copied to clipboard
akamaster
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.
Please include CIFAR100 results and pretrained models. Thanks.
This PR aims to add basic [**Weights and Biases**](https://wandb.ai/site) Metric Logging with minimal changes.
It seems that although there is a flag for pre-trained model in the trainer.py, but it is not used to load the model and the training proceeds from scratch. Note:...
Hello, Thank you very much for this repo. I'm looking for **trained** model parameters, do you happen to have it for resnet20 and resnet32? Thank you.
How many epochs did u run in order to obtain the accuracy/error you claimed? I haven't found you have documented that anywhere. If you could explain your training policy a...
Hello, thanks for your contribution. I run your code, but I can't obtain the result that you reported. Such as resnet20 in Cifar10, the accuracy is only 88.73. I hope...
Hi, When I tried to resume the training process, I was told that `'initial_lr' is not specified in param_groups[0] when resuming an optimizer`. So, I guess we have to feed...
While running evaluate mode directly through command line ">python trainer.py --arch resnet20 --pretrained --evaluate --print-freq 5 Files already downloaded and verified Test: [0/79] Time 13.405 (13.405) Loss 55.9279 (55.9279) Prec@1...
The previous normalization values for CIFAR-10 seem to be wrong. Source: [Correct Normalization Values for CIFAR-10](https://github.com/kuangliu/pytorch-cifar/issues/19#issue-268972488) The given models need to be re-run to get updated results (performance).
