CenterNet
CenterNet copied to clipboard
During the training, the following errors occurred:AttributeError: 'NoneType' object has no attribute 'shape'
Setting up data...
==> initializing coco 2017 val data.
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Loaded val 812 samples
==> initializing coco 2017 train data.
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
Loaded train 812 samples
Starting training...
ctdet/coco_dla/home/rc/anaconda3/envs/centerNet1/lib/python3.6/site-packages/torch/nn/functional.py:52: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
warnings.warn(warning.format(ret))
ctdet/coco_dla |################################| train: [1][100/101]|Tot: 0:03:18 |ETA: 0:00:02 |loss 5.1209 |hm_loss 3.8793 |wh_loss 9.5661 |off_loss 0.2850 |Data 0.141s(0.133s) |Net 1.964s
ctdet/coco_dla |################################| train: [2][100/101]|Tot: 0:03:15 |ETA: 0:00:02 |loss 3.5339 |hm_loss 2.6739 |wh_loss 5.9882 |off_loss 0.2611 |Data 0.141s(0.143s) |Net 1.931s
ctdet/coco_dla |################################| train: [3][100/101]|Tot: 0:03:15 |ETA: 0:00:02 |loss 3.3472 |hm_loss 2.5956 |wh_loss 4.9320 |off_loss 0.2584 |Data 0.143s(0.143s) |Net 1.934s
ctdet/coco_dla |################################| train: [4][100/101]|Tot: 0:03:15 |ETA: 0:00:02 |loss 3.2140 |hm_loss 2.4639 |wh_loss 4.9046 |off_loss 0.2596 |Data 0.146s(0.142s) |Net 1.938s
ctdet/coco_dla |################################| train: [5][100/101]|Tot: 0:03:15 |ETA: 0:00:02 |loss 3.1397 |hm_loss 2.4231 |wh_loss 4.6018 |off_loss 0.2565 |Data 0.143s(0.142s) |Net 1.939s
ctdet/coco_dlaTraceback (most recent call last):
File "main.py", line 102, in
I print(img), it's ok. So I don't know what's wrong,please help me!Thank you very much!
I have the same mistake,have you solved it?
make sure you got the correct image path. dataloader can't find the image with the path you give.
make sure you got the correct image path. dataloader can't find the image with the path you give.
The image path is correct. I have print (img), it has data. What I am puzzled about is that it didn't report a mistake at the beginning. It was after training several times that it made a mistake.
make sure you got the correct image path. dataloader can't find the image with the path you give.
The image path is correct. I have print (img), it has data. What I am puzzled about is that it didn't report a mistake at the beginning. It was after training several times that it made a mistake.
because the first paths are correct. and the path after several iters is wrong. or your image file is broken for that specific image
make sure you got the correct image path. dataloader can't find the image with the path you give.
The image path is correct. I have print (img), it has data. What I am puzzled about is that it didn't report a mistake at the beginning. It was after training several times that it made a mistake.
because the first paths are correct. and the path after several iters is wrong. or your image file is broken for that specific image
Sorry, I don't quite understand. The annotations tag of my dataset is to convert xml to coco's json format. So I think if the data path is wrong, it will go wrong together. Why is there a time when the path is correct? I don't know how to find this mistake, can you elaborate on it. Thank you very much!
I have the same problem with you ,have you solved it?thank you very much!
I have the same problem with you ,have you solved it?thank you very much!
I met same problem, do you solve it?
test.py in 33: img_path = os.path.join(self.img_dir, 'val/',img_info['file_name']), add 'val', it works