root@7128c9029a5b:~/AI-lab/power_dekor_danyang# python train.py[0] fold_i: 0 soft_labels is None soft_labels is None /opt/conda/lib/python3.8/site-packages/pytorch_lightning/utilities/warnings.py:18: RuntimeWarning: Displayed epoch numbers in the progress bar start from "1" until v0.6.x, but will start from "0" in v0.8.0. warnings.warn(*args, **kwargs) /opt/conda/lib/python3.8/site-packages/pytorch_lightning/utilities/warnings.py:18: UserWarning: The dataloader, train dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` in the `DataLoader` init to improve performance. warnings.warn(*args, **kwargs) /opt/conda/lib/python3.8/site-packages/pytorch_lightning/utilities/warnings.py:18: UserWarning: The dataloader, val dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` in the `DataLoader` init to improve performance. warnings.warn(*args, **kwargs) /opt/conda/lib/python3.8/site-packages/torch/nn/functional.py:780: UserWarning: Note that order of the arguments: ceil_mode and return_indices will changeto match the args list in nn.MaxPool2d in a future release. warnings.warn("Note that order of the arguments: ceil_mode and return_indices will change" Traceback (most recent call last): File "train.py", line 179, in trainer.fit(model, train_dataloader, val_dataloader) File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 704, in fit self.single_gpu_train(model) File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/distrib_parts.py", line 477, in single_gpu_train self.run_pretrain_routine(model) File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 864, in run_pretrain_routine self.train() File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 363, in train self.run_training_epoch() File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 435, in run_training_epoch _outputs = self.run_training_batch(batch, batch_idx) File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 604, in run_training_batch loss, batch_output = optimizer_closure() File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 571, in optimizer_closure output_dict = self.training_forward( File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 728, in training_forward output = self.model.training_step(*args) File "train.py", line 51, in training_step loss = self.criterion(scores, labels) File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/AI-lab/power_dekor_danyang/loss_function.py", line 16, in forward return torch.mean(torch.sum(-labels * self.log_softmax(preds), -1)) RuntimeError: The size of tensor a (5) must match the size of tensor b (2) at non-singleton dimension 1
修改models.py
5分类训练
num_class改为5
def __init__(self, num_class=5, emb_size=2048, s=16.0):
BinaryHead第一个参数修改为5
self.binary_head = BinaryHead(5, emb_size=2048, s=1)
