CNN practical notes
some notes on my training with CNN

Train CIFAR10

  • On 2019.12.6, I tried to use torchvision.models.resnet18 to train CIFAR10
  • Some findings in time sequential orders
  • Takeaway
    • weight decay is important, yet torch.optim disable it by default. set it to 1e-4 or 5e-4.
    • It's not preferrable to directly use torchvision.models or other pretrained model architectures on datasets other than ImageNet. That's what so called 'Hyperparameter tuning is important'.

Pretrained models

Copy link
On this page
Train CIFAR10
Pretrained models