Error in "bg"

[omizonly]

loading from scratch

0
#########################
Training epoch 0
Traceback (most recent call last):

File "/home/nd/Osman/Pytorch-CustomDataset-FasterRCNN-master/main.py", line 516, in
train(i)

File "/home/nd/Osman/Pytorch-CustomDataset-FasterRCNN-master/main.py", line 282, in train
for i,(image, boxes, labels , temp, num_pos) in enumerate(train_loader):

File "/home/nd/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()

File "/home/nd/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data
return self._process_data(data)

File "/home/nd/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data
data.reraise()

File "/home/nd/anaconda3/lib/python3.8/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)

TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/nd/anaconda3/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/home/nd/anaconda3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/nd/anaconda3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/nd/Osman/Pytorch-CustomDataset-FasterRCNN-master/dataset.py", line 60, in getitem
y_is_box_label, y_rpn_regr, num_pos = self.rpm.calc_rpn(boxes , labels, image_resize_size=self.image_resize_size)
File "/home/nd/Osman/Pytorch-CustomDataset-FasterRCNN-master/tools.py", line 146, in calc_rpn
if self.rev_label_map[labels[bbox_num]] != 'bg':
TypeError: unhashable type: 'list'

[ppriyank]

The error is originated here : https://github.com/ppriyank/Pytorch-CustomDataset-FasterRCNN/blob/master/tools.py#L146
Can you set up an pdb there?

at line 145, write:

import pdb
pdb.set_trace() 

and paste the output from

print(self.rev_label_map)
print(labels)
print(bbox_num)