一个bug：IndexError: index 2 is out of range

[starsky68]

假设训练5个类，在训练的时候每一帧图像对应的标签，类别号如果是0-4中间有缺失，比如标签中只有0类和2类，就会出现最后一个类别号越界的错误：
以下是我打印的一个models.py的第332行的cls_id, nID，以及334行的self.id_classifiers，
0 3==========
2 3==========
ModuleList(
(0): Linear(in_features=128, out_features=3, bias=True)
(1): Linear(in_features=128, out_features=3, bias=True)
) 33333333333333
Model Summary: 91 layers, 6.67257e+06 parameters, 6.67257e+06 gradients
Caching labels (1 found, 0 missing, 0 empty, 0 duplicate, for 1 images): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 979.06it/s]
Image sizes 384 - 832 train, 768 test
Using 0 dataloader workers
Starting training for 100 epochs...

 Epoch   gpu_mem      GIoU       obj       cls      reid     total   targets  img_size

0%| | 0/1 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 660, in
train() # train normally
File "train.py", line 452, in train
loss, loss_items = compute_loss_no_upsample(pred, reid_feat_out, targets, track_ids, model)
File "/home/11/YOLOV4_MCMOT-master/utils/utils.py", line 501, in compute_loss_no_upsample
fc_preds = model.id_classifiers[cls_id].forward(id_vects).contiguous()
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/modules/container.py", line 164, in getitem
return self._modules[self._get_abs_string_index(idx)]
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/modules/container.py", line 154, in _get_abs_string_index
raise IndexError('index {} is out of range'.format(idx))
IndexError: index 2 is out of range

该处是不是应该修改一下，以适应上述中的情况。
@CaptainEven