Description
``python3 train.py --datasets /home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/data/voc_dataset --validation_dataset /home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/data/voc_dataset
2025-02-28 22:51:54,488 - root - INFO - inpu size :320
priors nums:4420
2025-02-28 22:51:55,122 - root - INFO - Use Cuda.
2025-02-28 22:51:55,122 - root - INFO - Namespace(dataset_type='voc', datasets=['/home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/data/voc_dataset'], validation_dataset='/home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/data/voc_dataset', balance_data=False, net='RFB', freeze_base_net=False, freeze_net=False, lr=0.01, momentum=0.9, weight_decay=0.0005, gamma=0.1, base_net_lr=None, extra_layers_lr=None, base_net=None, pretrained_ssd=None, resume=None, scheduler='multi-step', milestones='80,100', t_max=120, batch_size=24, num_epochs=200, num_workers=4, validation_epochs=5, debug_steps=100, use_cuda=True, checkpoint_folder='models/', log_dir='./models/Ultra-Light(1MB)_&_Fast_Face_Detector/logs', cuda_index='0', power=2, overlap_threshold=0.35, optimizer_type='SGD', input_size=320)
2025-02-28 22:51:55,122 - root - INFO - Prepare training datasets.
2025-02-28 22:51:55,123 - root - INFO - No labels file, using default VOC classes.
2025-02-28 22:51:55,124 - root - INFO - Stored labels into file models/voc-model-labels.txt.
2025-02-28 22:51:55,124 - root - INFO - Train dataset size: 2582
2025-02-28 22:51:55,124 - root - INFO - Prepare Validation datasets.
2025-02-28 22:51:55,125 - root - INFO - No labels file, using default VOC classes.
2025-02-28 22:51:55,125 - root - INFO - validation dataset size: 277
2025-02-28 22:51:55,125 - root - INFO - Build network.
2025-02-28 22:51:55,266 - root - INFO - use gpu :[0]
2025-02-28 22:51:55,267 - root - INFO - Took 0.00 seconds to load the model.
2025-02-28 22:51:55,268 - root - INFO - Learning rate: 0.01, Base net learning rate: 0.01, Extra Layers learning rate: 0.01.
2025-02-28 22:51:55,268 - root - INFO - Uses MultiStepLR scheduler.
2025-02-28 22:51:55,268 - root - INFO - Start training from epoch 0.
Traceback (most recent call last):
File "/home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/train.py", line 357, in
train(train_loader, net, criterion, optimizer,
File "/home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/train.py", line 136, in train
for i, data in enumerate(loader):
File "/home/skylark/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 631, in next
data = self._next_data()
File "/home/skylark/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1346, in _next_data
return self._process_data(data)
File "/home/skylark/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1372, in _process_data
data.reraise()
File "/home/skylark/.local/lib/python3.10/site-packages/torch/_utils.py", line 722, in reraise
raise exception
IndexError: Caught IndexError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/skylark/.local/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/home/skylark/.local/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/skylark/.local/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/skylark/.local/lib/python3.10/site-packages/torch/utils/data/dataset.py", line 335, in getitem
return self.datasets[dataset_idx][sample_idx]
File "/home/skylark/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 "/home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/ssd/data_preprocessing.py", line 33, in call
return self.augment(img, boxes, labels)
File "/home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/transforms/transforms.py", line 619, in call
img, boxes, labels = t(img, boxes, labels)
File "/home/skylark/Ultra-Light-Fast-Generic-Face-Detector-1MB/vision/transforms/transforms.py", line 1034, in call
boxes[:, 0::2] = width - boxes[:, 2::-2]
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed