Modify the number of positive samples

[qxpBlog]

Sorry, @rm-wu @ga1i13o @gmberton @Enrico-Chiavassa . I want to modify the number of positive samples per round during training, but the following error occurred. How can I solve this problem：

Traceback (most recent call last):
  File "train.py", line 153, in <module>
    for images, triplets_local_indexes, _ in tqdm(triplets_dl, ncols=100):
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/tqdm/std.py", line 1130, in __iter__
    for obj in iterable:
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 630, in __next__
    data = self._next_data()
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1344, in _next_data
    return self._process_data(data)
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1370, in _process_data
    data.reraise()
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/_utils.py", line 706, in reraise
    raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 309, in _worker_loop
    data = fetcher.fetch(index)  # type: ignore[possibly-undefined]
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 52, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/data/qxp/VPR/vpr/datasets_ws.py", line 278, in __getitem__
    query_index, best_positive_index, neg_indexes = torch.split(self.triplets_global_indexes[index], (1, 1, self.negs_num_per_query))
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/functional.py", line 196, in split
    return tensor.split(split_size_or_sections, dim)
  File "/home/qxp/anaconda3/envs/vpr/lib/python3.8/site-packages/torch/_tensor.py", line 917, in split
    return torch._VF.split_with_sizes(self, split_size, dim)
RuntimeError: split_with_sizes expects split_sizes to sum exactly to 21 (input tensor's size at dimension 0), but got split_sizes=[1, 1, 10]

[gmberton]

Can you share the info.log file?