meliketoy / wide-resnet.pytorch

Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch

meliketoy/wide-resnet.pytorch Issues

Var of CIFAR10 wrong
Updated 6 months ago
Wide-ResNet 28-10-0.3 for CIAFR10 produced a low test accuracy
Updated a year ago
Activation functions in WRN?
Closed 2 years ago1
How to train WRN 34?
Updated 2 years ago
Checkpoints
Updated 2 years ago
Stride is Wrong
Updated 3 years ago1
Wrong Implementation
Updated 4 years ago2
Support for imagenet?
Updated 4 years ago3
Definition of Optimizer in train function
Updated 4 years ago
IndexError
Updated 5 years ago1
TypeError: can't multiply sequence by non-int of type 'float' in _wide_layer
Updated 5 years ago1
failed to reproduce the accuracy of WRN-28-10 on Cifar-10
Closed 5 years ago2
Unable to reproduce the accuracy of WRN-28-10 on Cifar-100
Updated 6 years ago23
These ResNets are not for CIFAR10
Updated 6 years ago
About dropout and shortcut in residual block
Updated 6 years ago