Zhu Tao

你好，在用GAN生成漫画头像的时候我遇到了一个问题。 一开始训练的时候GPU的利用率处于99%，训练速度很快，但随着训练的进行，GPU大部分时间利用率为0%，只有很少的时间处于计算状态，我测试了一下，发现图片的IO特别慢，读取一个batch需要耗费好几秒的时间，请问这是什么原因呢？

training process too slow

12

Hello, I use 1080Ti to train 200000 images, every image is 128*128. However, the speed of training is very slow, It takes me almost 4 hours to finish one epoch...

I just remove the LSTM layer, and there is no big difference between with and without LSTM. The point is that model can run faster without LSTM. left with LSTM,...

Table 3: Audio-Visual Speech Recognition and 1:25000 audio-video retrieval results with different supervisions.

1

Hi, after reading the paper, I am confused about the table 3. What is the meaning of visual acc, audio acc and combine acc? How did you calculate the result...

not good on Chinese words audio

5

Hi, I try the model on a piece of audio with the words of "广大党员干部正在积极学习。。。" But the result is not good. The images below are from test_sample3_fake_audio_B_0_0.png to test_sample3_fake_audio_B_0_17.png ...