Open hailuu684 opened 1 year ago
Hello, I also encountered this problem. The result of each batch is all 0, how do you solve this problem?
The reason could be at this line of code, the accuracy between src_logit and target_class = 0, so it still 100
The reason could be at this line of code, the accuracy between src_logit and target_class = 0, so it still 100
Hello, thanks for the reply. I have also seen similar answers, but I think this is just a display result. Will it affect the final map and various indicators? I trained dozens of epochs but the indicators are all 0
The reason could be at this line of code, the accuracy between src_logit and target_class = 0, so it still 100
Hello, thanks for the reply. I have also seen similar answers, but I think this is just a display result. Will it affect the final map and various indicators? I trained dozens of epochs but the indicators are all 0
你好,请问您解决这个全0的问题了吗?
modify the 71 line of datasets/coco.py : classes = [obj["category_id"] for obj in anno] to classes = [int(obj["category_id"]) for obj in anno]
If your class_error is always = 100, try to increase the batchSize, which is useful to me
i met the same question.i guess you can decrease the number of object querry.for me, it's useful.
Hi everyone, I am training the dert model using the coco dataset to see how it is going, I saw the class_error=100 in every batch when training in the first epoch. I just do not understand why is that?