/gpfs/projects/LynchGroup/spacewhale/git_spacewhale/spacewhale/shell_scripts
/gpfs/projects/LynchGroup/spacewhale
Tue May 21 12:00:42 EDT 2019
Now train resnext LR=0.2
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resneXt Your trained model will be named resnext_full256_lr2
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf6efcb00>
Your dataset size is: 12545
You have 2 classes in your dataset
------------------------------------------------------------------------------
Labels for the dataset are:
water = 0
whale = 1
------------------------------------------------------------------------------
Data loaded into gpu
------------------------------------------------------------------------------
/gpfs/projects/LynchGroup/spacewhale/git_spacewhale/spacewhale
Epoch 0/23
----------
torch.Size([32, 2, 1, 1])
torch.Size([32]) labels
Traceback (most recent call last):
  File "training_tester_weighted4.py", line 129, in <module>
    model_ft = s.train_model(opt, device, dataset_sizes, dataloaders, model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=opt.epochs)
  File "/gpfs/projects/LynchGroup/spacewhale/git_spacewhale/spacewhale/m_util2.py", line 128, in train_model
    loss = criterion(outputs, labels)
  File "/gpfs/projects/LynchGroup/spacewhale/space_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/gpfs/projects/LynchGroup/spacewhale/space_env/lib/python3.7/site-packages/torch/nn/modules/loss.py", line 862, in forward
    ignore_index=self.ignore_index, reduction=self.reduction)
  File "/gpfs/projects/LynchGroup/spacewhale/space_env/lib/python3.7/site-packages/torch/nn/functional.py", line 1550, in cross_entropy
    return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
  File "/gpfs/projects/LynchGroup/spacewhale/space_env/lib/python3.7/site-packages/torch/nn/functional.py", line 1409, in nll_loss
    return torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: 1only batches of spatial targets supported (non-empty 3D tensors) but got targets of size: : [32]
Tue May 21 12:00:49 EDT 2019
