CenterNet
CenterNet copied to clipboard
Duankaiwen
why the pull loss and push loss is 0.0 when training my own dataset?
When I train my own dataset, the pull loss and push loss is always 0.0. The log is: training loss at iteration 270: 0.08008845895528793 focal loss at iteration 270: 0.08008845895528793 pull loss at iteration 270: 0.0 push loss at iteration 270: 0.0 regr loss at iteration 270: 0.0 training loss at iteration 275: 0.07004862278699875 focal loss at iteration 275: 0.07004862278699875 pull loss at iteration 275: 0.0 push loss at iteration 275: 0.0 regr loss at iteration 275: 0.0 training loss at iteration 280: 0.06663033366203308 focal loss at iteration 280: 0.06663033366203308 pull loss at iteration 280: 0.0 push loss at iteration 280: 0.0 regr loss at iteration 280: 0.0 training loss at iteration 285: 0.07438242435455322 focal loss at iteration 285: 0.07438242435455322 pull loss at iteration 285: 0.0 push loss at iteration 285: 0.0 regr loss at iteration 285: 0.0
It seems something error! After, I test the model,there is also some errors like this:
Traceback (most recent call last): File "test.py", line 99, in test(testing_db, args.split, args.testiter, args.debug, args.suffix) File "test.py", line 61, in test testing(db, nnet, result_dir, debug=debug) File "/home/lz/python/CenterNet/CenterNet-master/test/coco.py", line 321, in testing return globals()[system_configs.sampling_function](db, nnet, result_dir, debug=debug) File "/home/lz/python/CenterNet/CenterNet-master/test/coco.py", line 317, in kp_detection db.evaluate(result_json, cls_ids, image_ids) File "/home/lz/python/CenterNet/CenterNet-master/db/coco.py", line 176, in evaluate coco_dets = coco.loadRes(result_json) File "data/coco/PythonAPI/pycocotools/coco.py", line 318, in loadRes if 'caption' in anns[0]: IndexError: list index out of range
Can anyone help me?Thanks a lot!!!
When I train my own dataset, the pull loss and push loss is always 0.0. The log is: training loss at iteration 270: 0.08008845895528793 focal loss at iteration 270: 0.08008845895528793 pull loss at iteration 270: 0.0 push loss at iteration 270: 0.0 regr loss at iteration 270: 0.0 training loss at iteration 275: 0.07004862278699875 focal loss at iteration 275: 0.07004862278699875 pull loss at iteration 275: 0.0 push loss at iteration 275: 0.0 regr loss at iteration 275: 0.0 training loss at iteration 280: 0.06663033366203308 focal loss at iteration 280: 0.06663033366203308 pull loss at iteration 280: 0.0 push loss at iteration 280: 0.0 regr loss at iteration 280: 0.0 training loss at iteration 285: 0.07438242435455322 focal loss at iteration 285: 0.07438242435455322 pull loss at iteration 285: 0.0 push loss at iteration 285: 0.0 regr loss at iteration 285: 0.0
It seems something error! After, I test the model,there is also some errors like this:
Traceback (most recent call last): File "test.py", line 99, in test(testing_db, args.split, args.testiter, args.debug, args.suffix) File "test.py", line 61, in test testing(db, nnet, result_dir, debug=debug) File "/home/lz/python/CenterNet/CenterNet-master/test/coco.py", line 321, in testing return globals()[system_configs.sampling_function](db, nnet, result_dir, debug=debug) File "/home/lz/python/CenterNet/CenterNet-master/test/coco.py", line 317, in kp_detection db.evaluate(result_json, cls_ids, image_ids) File "/home/lz/python/CenterNet/CenterNet-master/db/coco.py", line 176, in evaluate coco_dets = coco.loadRes(result_json) File "data/coco/PythonAPI/pycocotools/coco.py", line 318, in loadRes if 'caption' in anns[0]: IndexError: list index out of range
Can anyone help me?Thanks a lot!!!
I have figured out the problem. It's because the boxes ids of my annotations file are all the same.
Have you sloved the problem? I have the same problem with you, and I am sure that the boxes ids of my annotation file are different. Can you help me?
I have figured out the problem. It's because the boxes ids of my annotations file are all the same.
what are boxes ids?
