Have you trained the model for the UCF101 from scratch?

Open lixianhang opened this issue 7 years ago • 2 comments

I just trained for 45 epochs and set LR 0.01 for UCF101, but I got the really terrible result. Firstly the training loss is stable around 4, but cannot get lower(because the dataset is small, it should be overfitted). And second, the test accuracy is around 1% even after 45 epochs. I followed your instruction to process the dataset. I don't know where is wrong. Could you please tell me your result if you have?

Nov 28 '18 07:11 lixianhang

I have met the same problem. How did you solve the problem? Can you please share?

Jan 19 '19 02:01 qingxiaoli

Hello , it might be too late. I found that learning rate is decreasing too fast. Change gamma 0.1 to big number such as 0.9. It will be better

Oct 13 '19 08:10 yechanp