TypeError: len() of a 0-d tensor

[jamiechoi1995]

Traceback (most recent call last):
File "generate_tsv.py", line 476, in
generate_tsv(args.outfile, image_ids, args)
File "generate_tsv.py", line 459, in generate_tsv
writer.writerow(get_detections_from_im(fasterRCNN, classes, im_file, image_id, args))
File "generate_tsv.py", line 347, in get_detections_from_im
if len(keep_boxes) < MIN_BOXES:
File "anaconda2/envs/py3.6pytorch1.0/lib/python3.6/site-packages/torch/tensor.
py", line 411, in len
raise TypeError("len() of a 0-d tensor")
TypeError: len() of a 0-d tensor

when keep_boxes only have 1 value that is >0,
torch.squeeze(torch.nonzero(keep_boxes)) will generate a tensor with dim() = 0

Code to reproduce:
keep_boxes=torch.tensor([0,1,0,0])
len(torch.squeeze(torch.nonzero(keep_boxes)))

[Kilichbek]

In my case, this error was caused when the model could not detect any object in the image.
I solved this by:
Skipping that "bad" image during feature extraction or changing the confidence threshold for detection.

[mzshuo]

Traceback (most recent call last):
File "generate_tsv.py", line 476, in
generate_tsv(args.outfile, image_ids, args)
File "generate_tsv.py", line 459, in generate_tsv
writer.writerow(get_detections_from_im(fasterRCNN, classes, im_file, image_id, args))
File "generate_tsv.py", line 347, in get_detections_from_im
if len(keep_boxes) < MIN_BOXES:
File "anaconda2/envs/py3.6pytorch1.0/lib/python3.6/site-packages/torch/tensor.
py", line 411, in len
raise TypeError("len() of a 0-d tensor")
TypeError: len() of a 0-d tensor

when keep_boxes only have 1 value that is >0,
torch.squeeze(torch.nonzero(keep_boxes)) will generate a tensor with dim() = 0

Code to reproduce:
keep_boxes=torch.tensor([0,1,0,0])
len(torch.squeeze(torch.nonzero(keep_boxes)))

That perfectly works. Thanks so much.