pytorch-classification

pytorch-classification copied to clipboard

Hi，thank you for your code firstly but I'm confused why you using ShortcutB(1*1 conv) when the size of feature map is halved. Because as far as I know, ShortcutA(insert 0)...

I-Doctor

Add Pytorch 4.x/1.0 compatibility, Visual Studio solution files

1

This PR adds on the top of https://github.com/bearpaw/pytorch-classification/pull/9. - Add Pytorch 4.1 and 1.0 compatibility (mainly use `item()` instead of [0] and `torch.no_grad()`). - Also added VS solution files for...

sytelus

How to use muti-gpus ？

1

what's the command to use muti-gpus?

MrLinNing

The torchvision includes many networks. (alexnet, vgg11, etc...) I could do run your sample according to TRAINING.md. But I couldn't do run other networks. my status ) $ python imagenet.py...

edwardcho

Thank you for sharing this codes, I want to use your WRN model to extract features from cifar 100 and feed them into the some recurrent neural network for some...

MehrdadHMT

if I want to run DenseNet-BC (L=190, k=40)  on cifar100 and batch_size=64,How much memory is needed？How about ResNeXt-29, 16x64？

jianghuairong

I don't have gpu in my laptop, is there anyway i can run it on my cpu? I get this error: 

debadridtt

Accuracy of training

2

Hi, I am try to use your modified model on cifar100. But my alexnet's accuracy just can be around 42%; and vgg19_bn just can be 62%around ,63.46% most when the...

Chinese-xingyi

Hello, I was looking to use the Imagenet.py file for training a Resnet50 model from scratch. I was getting confused as to how many epochs should I train my network...

nbansal90

Hi, I have using the Resnet18 to training imagenet, however I find zero gpu usage when train imagenet. Is it also the same when you train it?

Lan1991Xu