Closed boxyao closed 4 years ago
Make the obtained gradient larger and speed up training,the value of raw_features is too small
Is 100 a experience value?
I have ran the code. The test accuracy is very well, but the train and val prec@1 and prec@5 are very samll values, such as 1.4, 1.5. Is it right? Is there something wrong with my trainning?
Is 100 a experience value?
Maybe,I followed the settings in the official repo, ws_dan
I have ran the code. The test accuracy is very well, but the train and val prec@1 and prec@5 are very samll values, such as 1.4, 1.5. Is it right? Is there something wrong with my trainning?
I think it is not normal, maybe you can check it carefully. 1.4 1.5 may be the loss values, not precisions
pooling_features = raw_features*100 , Why multiply raw_features by 100?