ghost
commented
3 years ago https://github.com/takumayagi/openmax-cifar10/blob/9d7ae83a8e1ca1692e15efcbed95b5058511ef2e/dataset.py#L134
On Windows platform, please use the SerialIterator instead of the MultiprocessIterator.
Hi all and @takumayagi ,
I get the following error when I try to run:
For model selection
sh scripts/train_val.sh
`Train: 50000, Valid: 10000 Traceback (most recent call last): File "C:/Users/RAR7ABT/pj-val-ml/pjval_ml/OSR/openmax/main.py", line 49, in
main()
File "C:/Users/RAR7ABT/pj-val-ml/pjval_ml/OSR/openmax/main.py", line 22, in main
train(opt, i)
File "C:/Users/RAR7ABT/pj-val-ml/pjval_ml/OSR/openmax/main.py", line 35, in train
train_loss, train_top1 = trainer.train(epoch)
File "C:\Users\RAR7ABT\pj-val-ml\pjval_ml\OSR\openmax\train.py", line 27, in train
for i, batch in enumerate(self.train_iter):
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\site-packages\chainer\iterators\multiprocess_iterator.py", line 149, in next
self._prefetch_loop.launch_thread()
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\site-packages\chainer\iterators\multiprocess_iterator.py", line 433, in launch_thread
initargs=(self.dataset, self.mem_size, self.mem_bulk))
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\multiprocessing\context.py", line 119, in Pool
context=self.get_context())
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\multiprocessing\pool.py", line 174, in init
self._repopulate_pool()
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\multiprocessing\pool.py", line 239, in _repopulate_pool
w.start()
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\multiprocessing\popen_spawn_win32.py", line 65, in init
reduction.dump(process_obj, to_child)
File "C:\Users\RAR7ABT\AppData\Local\conda\conda\envs\test\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'normalize..f'
Process finished with exit code 1 `
Any help would be appreciated. Thank you!