Kaiwen Duan comments

Results 110 comments of


                                            Kaiwen Duan

RuntimeError: invalid argument 5: k not in range for dimension

@WuChannn Comment out line 147 in test/coco.py

RuntimeError: invalid argument 5: k not in range for dimension

@WuChannn 1.'top_k' maybe too small. 2. how much iter does your model train? 3.. the class number in your own dataset should start from 1. 4. modify some codes in...

RuntimeError: invalid argument 5: k not in range for dimension

@WuChannn Oh，I see

RuntimeError: invalid argument 5: k not in range for dimension

@WuChannn 'kp_detection' is just a function name in sample/coco.py, ‘kp_categories’ is not used, you can delete it. 'db.class_name' is defined in db/coco.py, you can step through each line of code...

Why My map all 0?

@ACbccc 200 iterations is too short

why the pull loss and push loss is 0.0 when training my own dataset?

Can I see your full log?

why the pull loss and push loss is 0.0 when training my own dataset?

@Troy0425 Great!

The more weights

sorry, the trained models are temporarily unavailable

errors on training custom instance segmentation dataset

@kklots add coco_lsvr.py to code/configs/_base_/datasets, modify coco.py at code/mmdet/datasets and loading.py and transforms.py at code/mmdet/datasets/pipelines

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation:

what's your pytorch version?