gistfile1.txt

fold:  0
 0.00% [0/7 00:00<00:00]
epoch	train_loss	valid_loss	dice	time
 Interrupted
---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-21-2b9600a80866> in <module>
     15     lr = 1e-4
     16     #learn.load('fold_4')
---> 17     learn.fit_one_cycle(7, lr, callbacks = [AccumulateStep(learn,n_acc)])
     18 
     19     #fit entire model with saving on the best epoch

~/.local/lib/python3.6/site-packages/fastai/train.py in fit_one_cycle(learn, cyc_len, max_lr, moms, div_factor, pct_start, final_div, wd, callbacks, tot_epochs, start_epoch)
     20     callbacks.append(OneCycleScheduler(learn, max_lr, moms=moms, div_factor=div_factor, pct_start=pct_start,
     21                                        final_div=final_div, tot_epochs=tot_epochs, start_epoch=start_epoch))
---> 22     learn.fit(cyc_len, max_lr, wd=wd, callbacks=callbacks)
     23 
     24 def lr_find(learn:Learner, start_lr:Floats=1e-7, end_lr:Floats=10, num_it:int=100, stop_div:bool=True, wd:float=None):

~/.local/lib/python3.6/site-packages/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks)
    200         callbacks = [cb(self) for cb in self.callback_fns + listify(defaults.extra_callback_fns)] + listify(callbacks)
    201         self.cb_fns_registered = True
--> 202         fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
    203 
    204     def create_opt(self, lr:Floats, wd:Floats=0.)->None:

~/.local/lib/python3.6/site-packages/fastai/basic_train.py in fit(epochs, learn, callbacks, metrics)
     99             for xb,yb in progress_bar(learn.data.train_dl, parent=pbar):
    100                 xb, yb = cb_handler.on_batch_begin(xb, yb)
--> 101                 loss = loss_batch(learn.model, xb, yb, learn.loss_func, learn.opt, cb_handler)
    102                 if cb_handler.on_batch_end(loss): break
    103 

~/.local/lib/python3.6/site-packages/fastai/basic_train.py in loss_batch(model, xb, yb, loss_func, opt, cb_handler)
     24     if not is_listy(xb): xb = [xb]
     25     if not is_listy(yb): yb = [yb]
---> 26     out = model(*xb)
     27     out = cb_handler.on_loss_begin(out)
     28 

~/.local/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    545             result = self._slow_forward(*input, **kwargs)
    546         else:
--> 547             result = self.forward(*input, **kwargs)
    548         for hook in self._forward_hooks.values():
    549             hook_result = hook(self, input, result)

~/.local/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py in forward(self, *inputs, **kwargs)
    150             return self.module(*inputs[0], **kwargs[0])
    151         replicas = self.replicate(self.module, self.device_ids[:len(inputs)])
--> 152         outputs = self.parallel_apply(replicas, inputs, kwargs)
    153         return self.gather(outputs, self.output_device)
    154 

~/.local/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py in parallel_apply(self, replicas, inputs, kwargs)
    160 
    161     def parallel_apply(self, replicas, inputs, kwargs):
--> 162         return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
    163 
    164     def gather(self, outputs, output_device):

~/.local/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py in parallel_apply(modules, inputs, kwargs_tup, devices)
     83         output = results[i]
     84         if isinstance(output, ExceptionWrapper):
---> 85             output.reraise()
     86         outputs.append(output)
     87     return outputs

~/.local/lib/python3.6/site-packages/torch/_utils.py in reraise(self)
    367             # (https://bugs.python.org/issue2651), so we work around it.
    368             msg = KeyErrorMessage(msg)
--> 369         raise self.exc_type(msg)

RuntimeError: Caught RuntimeError in replica 1 on device 1.
Original Traceback (most recent call last):
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker
    output = module(*input, **kwargs)
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/fastai/layers.py", line 136, in forward
    nres = l(res)
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/fastai/vision/models/unet.py", line 33, in forward
    cat_x = self.relu(torch.cat([up_out, self.bn(s)], dim=1))
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 81, in forward
    exponential_average_factor, self.eps)
  File "/home/jupyter-judy/.local/lib/python3.6/site-packages/torch/nn/functional.py", line 1656, in batch_norm
    training, momentum, eps, torch.backends.cudnn.enabled
RuntimeError: Expected tensor for argument #1 'input' to have the same device as tensor for argument #2 'weight'; but device 0 does not equal 1 (while checking arguments for cudnn_batch_norm)