Chestnut

How to optimize?

1

hi~ Thanks for your repository! I construct a autoencoder for CT image. I use the loss function called SigmoidCrossEntropyLoss in Caffe. Then I got loss about 500k. It is impossoble...

Could not train on v100

4

## PLEASE FOLLOW THESE INSTRUCTIONS BEFORE POSTING 1. **Read the README.md thoroughly ! README.md is not a decoration.** 2. Please search existing *open and closed* issues in case your issue...

## PLEASE FOLLOW THESE INSTRUCTIONS BEFORE POSTING 1. **Read the README.md thoroughly ! README.md is not a decoration.** 2. Please search existing *open and closed* issues in case your issue...

about softmax_loss layer

3

hi~ It is very appreciated that you release this code. It is very helpful for my research. but I have the question about the softmax_loss layer. in some situation that...

patch training

1

hi~ I wonder if this can support the patch training, not the whole image?

questions about how to get dataset ready for testing or training on my own

1

hi, thanks for your fancy work! I am now trying to put the testset on my own I download the testset as you say in 4kmedia.org For HDR video: 1....

Resnet50 out of memory

2

hi~ I am run your code in my machine which is 12G titanx. datasets is Coco. when I am traing the resnet 50 +3stage, It could not work, It will...

Hi~ I have noticed that you use the sigmoid cross entropy loss function to learning the autoencoder. But if my data is a RGB image, It is impossible to use...

Thanks for your sharing this! I read your code and blog and found that when encoder, convolutions before maxpooling will repeat, but in decoder you just do convolution once on...