艾因•利奇曼@利奇曼冒险团

Which hell versions of CUDA and cuDNN does project support?

2

I use CUDA 8.0 and cuDNN v5. I cannot make the project for some issues of API inconsistency like: CXX src/caffe/util/cudnn.cpp In file included from src/caffe/util/cudnn.cpp:2:0: ./include/caffe/util/cudnn.hpp: In function ‘void...

兄弟我敬你是条汉子

1

RT

Incorrectly dealing with batch normalization layers

1

The elephas calculates the deltas of the weights by simple subtraction. This strategy is efficient for the conv2d layers and dense layers. However, modern neural networks always contain batch normalization...

This model takes 500+ GFLOPS, it is very hard to land in industry world.

有什么加速的方法吗？到现在为止，四五年前的Wav2Lip还是性价比最高的方案啊。

def get_segmented_mels(self, spec, start_frame): mels = [] assert syncnet_T == 5 start_frame_num = self.get_frame_id(start_frame) + 1 # 0-indexing ---> 1-indexing if start_frame_num - 2 < 0: return None for i...

I am planning finetune the model with my own dataset. [email protected]

 里面的东西是空的，这个该怎么解