ResNet issues

Update train_resnet.py

mx.model.FeedForward is deprecated in the latest master. Changing the same with mx.mod.Module. Kindly check and comment. Please feel free to make necessary changes.

arundasan91

Why does the ResNext use original Residual Block instead of pre-activation residual block？

In the Identity Mapping, the author claimed that pre-activation is better than post-activation, but i find that in the ResNext , the residual blocks are the original post activation residual...

Itsanewday

Trouble replicating results for ResNet18 on ImageNet 1k

1

I'm trying to replicate your results for ResNet18 on ImageNet 1k. I'm using the default hyperparameters in your `train_resnet.py` and all of the same augmenters (for aug-level=2), but can't achieve...

dyelax

Why retrain at about 95 epoch with data aug disabled

3

Hi, I am trying to reproduce the resnet imagenet result on mxnet. I noticed that you have successfully reproduced the resnet [results](https://github.com/facebook/fb.resnet.torch) from facebook, but you mentioned that > when...

DeppMeng

无法下载resnet34和resnet18的预处理模型和json文件

无法下载resnet34和resnet18的预处理模型和json文件，请问可以发我邮箱[email protected]吗

yjhuasheng

Why can't I download the model resnet-50?

1

Is the download link invalid?

frogcode1024

Why we can not get the same curves especially on ResNet 34 and ResNet 101 ?

12

Thank you for your Resnet implementation with MxNet. This is a good example especially for beginner. I still follow this project and follow the train steps for imagenet. We want...

ghost