Closed shanyun123456 closed 3 years ago
taining from scatch on cocodatasets, not finetune
We used 140 epochs. You can find the settings that we used exactly in the experiments folder.
what about the loss of training
The heatmap loss is usually on the order of 1e-4 and the offset loss is usually on the order of 1e-5.
Thanks, By the way, What the loss of training did you get when you finish the 140 epochs of training?
For the model with HRNet-W48 backbone, the AP on COCO validation with multi-scale testing is 72.3, the heatmap loss is 1.752e-4 and the offset loss is 4.764e-5.
ok , thank you!
The loss of training is very small and decreases slowly when i finetune model on cocodatasets. Is't normal? and how many epoches do you set?