xiatao

Question about the results in detection task

1

When comparing with sota in detection task, did you pretrain your model in ImageNet?

About the training

1

Nice job !, i wonder that what is your training datasets? I cant find in your paper and code

Mul

3

multimodality video analysis v1.0

python3.6 cannot use pymatting and report pymatting_dot cannot found in ubuntu [Question❓]

1

python3.6 cannot use pymatting and report pymatting_dot cannot found in ubuntu, but python3.8 can work

解决 SPD_yolov5, parse_model错误

I can only get 43.61% accuracy in Somethingv1

5

I can only get 43.61% Accuracy in somethingv1, limited by my hardware i only use one GPU with batch-size = 16. why i cant get ur result ? Here is...

if val_step > 0 anb val_step != checkpoint_step there will be wrong to

What's the difference between the DIM and RWP ?

4

I train the network using the DIM config, but got very poor results, This is my train loss curve, and should i use the RWP config ? ![Uploading 截屏2021-07-26 下午7.07.31.png…]()