Error while training

[Saif0765]

/content/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/transforms/transforms.py:383: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
mode = random.choice(self.sample_options)
Traceback (most recent call last):
File "train.py", line 358, in
device=DEVICE, debug_steps=args.debug_steps, epoch=epoch)
File "train.py", line 136, in train
for i, data in enumerate(loader):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 681, in next
data = self._next_data()
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1376, in _next_data
return self._process_data(data)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1402, in _process_data
data.reraise()
File "/usr/local/lib/python3.7/dist-packages/torch/_utils.py", line 461, in reraise
raise exception
IndexError: Caught IndexError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataset.py", line 235, in getitem
return self.datasets[dataset_idx][sample_idx]
File "/content/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/datasets/voc_dataset.py", line 61, in getitem
image, boxes, labels = self.transform(image, boxes, labels)
File "/content/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/ssd/data_preprocessing.py", line 33, in call
return self.augment(img, boxes, labels)
File "/content/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/transforms/transforms.py", line 75, in call
img, boxes, labels = t(img, boxes, labels)
File "/content/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/transforms/transforms.py", line 129, in call
boxes[:, 0] /= width
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed

[lukseny]

I faced the same problem
It turned out that there was error in annotation preparation
In annotations I had [X, Y] classes, so I was training model for class [X] while my xml_s had examples of images with only class [Y], so boxes land labels had and empty list
Annotation revision and cleaning worked for me