E:\va>python train.py --epochs 3001 --batch_size 32 --checkpoint_path data/save --feats_dir data/feats/resnet152 --model S2VTAttModel --with_c3d 0 --dim_vid 2048 save opt details to data/save\opt_info.json vocab size is 6019 number of train videos: 3200 number of val videos: 200 number of test videos: 1000 load feats from ['data/feats/resnet152'] max sequence length in data is 28 vocab size is 6019 number of train videos: 3200 number of val videos: 200 number of test videos: 1000 load feats from ['data/feats/resnet152'] max sequence length in data is 28 D:\Python\lib\site-packages\torch\nn\modules\rnn.py:62: UserWarning: dropout option adds dropout after all but last recurrent layer, so non-zero dropout expects num_layers greater than 1, but got dropout=0.5 and num_layers=1 warnings.warn("dropout option adds dropout after all but last " D:\Python\lib\site-packages\torch\nn_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) D:\Python\lib\site-packages\torch\optim\lr_scheduler.py:129: UserWarning: Detected call of lr_scheduler.step() before optimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step() before lr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate warnings.warn("Detected call of lr_scheduler.step() before optimizer.step(). " 新轮次 0 正在训练…… 0%| | 0/100 [00:00<?, ?it/s]D:\Python\lib\site-packages\torch\nn\functional.py:1794: UserWarning: nn.functional.tanh is deprecated. Use torch.tanh instead. warnings.warn("nn.functional.tanh is deprecated. Use torch.tanh instead.") 100%|████████████████████████████████████████████████████████████████████████████████| 100/100 [00:17<00:00, 5.82it/s] 轮次 0 train_loss = 48.52919979095459 模型保存到 data/save\model_0.pth 100%|████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:00<00:00, 20.43it/s] 轮次 0 val_loss = 42.59846823556082 E:\va\train.py:51: FutureWarning: pandas.io.json.json_normalize is deprecated, use pandas.json_normalize instead answer_dataframe = json_normalize( Traceback (most recent call last): File "E:\va\train.py", line 219, in main(opt) File "E:\va\train.py", line 205, in main train(dataloader_train, dataloader_val, dataset_val, model, crit, File "E:\va\train.py", line 152, in train validate(model, utils.LanguageModelCriterion(), File "E:\va\train.py", line 70, in validate valid_score = scorer.score(answers, seq_outputs, seq_outputs.keys()) File "E:\va\misc\cocoeval.py", line 85, in score score, scores = scorer.compute_score(gts, res) File "E:\va\coco-caption\pycocoevalcap\meteor\meteor.py", line 41, in compute_score self.meteor_p.stdin.flush() OSError: [Errno 22] Invalid argument

batch_size 大于1就会出现这个错误，跑不起来

Traceback (most recent call last): File "D:/video-caption/6/yet-another-video-caption-private-main/makedata.py", line 31, in train_videos[i+NTRAIN]["split"] = "val" IndexError: list index out of range 请问怎么解决啊蟹蟹

训练过程中遇到了错误

新轮次 42 正在训练…… 0%| | 0/100 [00:00<?, ?it/s]/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/nn/functional.py:1340: UserWarning: nn.functional.tanh is deprecated. Use torch.tanh instead. warnings.warn("nn.functional.tanh is deprecated. Use torch.tanh instead.") 67%|██████████████████████████████████████████████████████████████████████████████████████████████▍ | 67/100 [00:13<00:11, 2.78it/s]Traceback (most recent call last): File "train.py", line 245, in main(opt) File "train.py", line 232, in main optimizer, exp_lr_scheduler, opt, rl_crit) File "train.py", line 130, in train for data in tqdm(loader): File "/root/miniconda3/envs/myconda/lib/python3.7/site-packages/tqdm/std.py", line 1104, in iter for obj in iterable: File "/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 346, in next data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/root/miniconda3/envs/myconda/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 "/root/miniconda3/envs/myconda/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 "/yavc/dataloader.py", line 61, in getitem fc_feat.append(np.load(os.path.join(dir, 'G%05d.npy' % (ix)))) File "/root/miniconda3/envs/myconda/lib/python3.7/site-packages/numpy/lib/npyio.py", line 457, in load raise ValueError("Cannot load file containing pickled data " ValueError: Cannot load file containing pickled data when allow_pickle=False 67%|██████████████████████████████████████████████████████████████████████████████████████████████▍ | 67/100 [00:13<00:06, 4.98it/s]

记得找个时间修

Traceback (most recent call last): File "D:/video-caption/6/yet-another-video-caption-private-main/makedata.py", line 31, in train_videos[i+NTRAIN]["split"] = "val" IndexError: list index out of range 请问怎么解决啊蟹蟹