Zhiqiang Lang

oh, really thanks for answer~ but, emmmm, i also refer to another implement: https://github.com/kuangliu/pytorch-cifar/blob/master/models/resnext.py And the numbers of conv with stride 3 is less than that stride 1, even though...

Yes, i think when `--cardinality 32 --widen_factor 4 --depth 50 --base_width 4`, it is right. but in your [train.py](https://github.com/prlz77/ResNeXt.pytorch/blob/master/train.py), `--cardinality 8--widen_factor 4 --depth 29--base_width 64`, i got : ` (stage_1):...

Running the torch code is a bit troublesome, but i think you are right. I test a total of three implement code: yours: https://github.com/prlz77/ResNeXt.pytorch/blob/master/models/model.py https://github.com/kuangliu/pytorch-cifar/blob/master/models/resnext.py https://github.com/D-X-Y/ResNeXt-DenseNet/blob/master/models/resnext.py And your network architecture...

Oh, I am very sorry to see your message so late. But I can't reproduce this problem. I think maybe you made some mistakes in the settings, or the problems...