wenxinxu / resnet-in-tensorflow

Re-implement Kaiming He's deep residual networks in tensorflow. Can be trained with cifar10.
MIT License
828 stars 276 forks source link

Why conv1 in first block is not followed by batch norm and relu #26

Open ghost opened 6 years ago

ghost commented 6 years ago

https://github.com/wenxinxu/resnet-in-tensorflow/blob/8ba8d8905e099cd7e1b1cf1f84b89f603f7613a0/resnet.py#L136

Can you please highlight the necessary section in the paper or in the original implementation.

Thank you