关于训练coco数据集的问题

[Standdrinkmilk]

你好，请问下我处理完coco数据集后，训练过程如下报错，能帮我看看是什么原因吗？ [2021-10-14 12:47:48,068-rk0-distributed.py#131] gradients method is sum [2021-10-14 12:49:28,001-rk0-train.py#241] Epoch: [1][20/11904] lr: 0.001000 batch_time: 4.661432 (5.191130) data_time: 0.000113 (0.144506) cls_loss: 0.493952 (0.575097) loc_loss: 0.998612 (0.998525) total_loss: 1.492564 (1.573622) [2021-10-14 12:49:28,001-rk0-log_helper.py#105] Progress: 20 / 238080 [0%], Speed: 5.191 s/iter, ETA 14:07:16 (D:H:M)

[2021-10-14 12:51:10,277-rk0-train.py#241] Epoch: [1][40/11904] lr: 0.001000 batch_time: 4.780557 (5.053296) data_time: 0.000125 (0.072318) cls_loss: 0.426808 (0.500939) loc_loss: 0.998599 (0.998491) total_loss: 1.425407 (1.499430) [2021-10-14 12:51:10,278-rk0-log_helper.py#105] Progress: 40 / 238080 [0%], Speed: 5.053 s/iter, ETA 13:22:08 (D:H:M)

Traceback (most recent call last): File "../../tools/train.py", line 310, in main() File "../../tools/train.py", line 305, in main train(train_loader, dist_model, optimizer, lr_scheduler, tb_writer) File "../../tools/train.py", line 168, in train for idx, data in enumerate(train_loader): File "/home/zyh/anaconda3/envs/siamban/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 819, in next return self._process_data(data) File "/home/zyh/anaconda3/envs/siamban/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data data.reraise() File "/home/zyh/anaconda3/envs/siamban/lib/python3.7/site-packages/torch/_utils.py", line 385, in reraise raise self.exc_type(msg) AttributeError: Caught AttributeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/zyh/anaconda3/envs/siamban/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/home/zyh/anaconda3/envs/siamban/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/zyh/anaconda3/envs/siamban/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/zyh/Code/siamban/siamban/datasets/dataset.py", line 253, in getitem template_box = self._get_bbox(template_image, template[1]) File "/home/zyh/Code/siamban/siamban/datasets/dataset.py", line 214, in _get_bbox imh, imw = image.shape[:2] AttributeError: 'NoneType' object has no attribute 'shape'

[sai-fu]

你好，训练过程有出现这个错误吗 AssertionError: load NONE from pretrained checkpoint

[zhengbangyan]

你好 我也出现了这个错误 请问一下是怎么解决的呢

[sai-fu]

你好 我也出现了这个错误 请问一下是怎么解决的呢 数据集格式有点问题，我用的csdn上别人裁剪好的数据集

[xuexiaodemenggubao]

请问这个代码怎么改成单gpu训练呢