Kevin43614

您好 我想請問一下訓練時 training loss 總是大於 validation loss 是有可能的嗎?

Discriminative ROI Pooling

5

Hello I want to ask one question about your paper. You say you use a pooling size of 7 × 7 (where k = 7) for classification, so "light-weight offset...

Hi, here has one question. In your paper, you say if pseudo IoU value > threshold then assign this point as positive sample. Now I want to ask if there...

您好，看完您的paper覺得挺有趣的 因此想作一點實驗 但發現您的config檔按裡沒有loss ，想請問您當初loss怎麼弄得?