Can't train the model?
fdujay opened this issue · comments
(base) davis@davis-MS-7B17:~/Network/EMANet-master$ python train.py
2019-08-31 13:50:14,703 - INFO - set log dir as ./logdir
2019-08-31 13:50:14,703 - INFO - set model dir as ./models
2019-08-31 13:50:17,131 - ERROR - No checkpoint ./models/latest.pth!
The Training step is stopped, so I have to Keyboard Interrupt it...
Does anybody know how to solve it?
I have met the other error:
v = obj.cuda(dev, async=True)
^
SyntaxError: invalid syntax
Solving it by exchanging "async" by "non_blocking", because 'async' is a reserved word in Python >= 3.7
(base) davis@davis-MS-7B17:~/Network/EMANet-master$ python train.py
2019-08-31 13:50:14,703 - INFO - set log dir as ./logdir
2019-08-31 13:50:14,703 - INFO - set model dir as ./models
2019-08-31 13:50:17,131 - ERROR - No checkpoint ./models/latest.pth!The Training step is stopped, so I have to Keyboard Interrupt it...
Does anybody know how to solve it?
As the GPUs are loading model sequentially, you may need to wait for around 20s, and then the training process will start.
I have met the other error:
v = obj.cuda(dev, async=True)
^
SyntaxError: invalid syntaxSolving it by exchanging "async" by "non_blocking", because 'async' is a reserved word in Python >= 3.7
v = obj.cuda(dev, async=True) is not included in my repo, and I haven't seed similar problems.