Yili Zhao
Yili Zhao
This is my jupyter notebook softmax prediction:  It seems that the prediction was wrong.
I also have this question.
The service is still down.
I also has this problem, so I think maybe this caffe version doesn't support new versions of cuDNN.
I also tried g++ with Ubuntu 18.04, but get some errors when compiling `thunk_code_x64.cpp`.
It seems that `call_thunk.cpp` includes `"call_thunk.h"`, and `call_thunk.h` includes `thunk_code_x64.cpp`.
Same issue for me. @auroua 's fix works. Thanks!
https://github.com/YimianDai/iNSFC/issues/14#issuecomment-607812023
@akanimax I note that `DataLoader` has a `FoldersDistributedDataset` class and a `get_data_loader` method. Should I use them? I also note that `train_network.py` can load a configure file like `celeba-hq.conf`. For...
@akanimax 1. Since every folder in my custom dataset represents a separate class, so I think the training is *Conditional ProGAN*. 2. By the way, does the training need every...