itijyou / gaitrecog Goto Github PK

when running this project,I met these problems and didn't know how to solve it.
Error codes are as follows:
epoch train_loss valid_loss accuracy recog_acc time
Traceback (most recent call last):
File "train_on_gei.py", line 389, in
trained:Param("Load from trained model", str)=None,
File "G:\Anaconda3\lib\site-packages\fastai\script.py", line 40, in call_parse
func(**args.dict)
File "train_on_gei.py", line 417, in main
Traceback (most recent call last):
File "", line 1, in
learn.fit(epochs, 1)
File "G:\Anaconda3\lib\site-packages\fastai\basic_train.py", line 200, in fit
File "G:\Anaconda3\lib\multiprocessing\spawn.py", line 105, in spawn_main
fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)exitcode = _main(fd)

File "G:\Anaconda3\lib\site-packages\fastai\basic_train.py", line 99, in fit
File "G:\Anaconda3\lib\multiprocessing\spawn.py", line 115, in _main
for xb,yb in progress_bar(learn.data.train_dl, parent=pbar):
self = reduction.pickle.load(from_parent) File "G:\Anaconda3\lib\site-packages\fastprogress\fastprogress.py", line 47, in iter

EOFError: Ran out of inputraise e

File "G:\Anaconda3\lib\site-packages\fastprogress\fastprogress.py", line 41, in iter
for i,o in enumerate(self.gen):
File "G:\Anaconda3\lib\site-packages\fastai\basic_data.py", line 75, in iter
for b in self.dl: yield self.proc_batch(b)
File "G:\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
return _MultiProcessingDataLoaderIter(self)
File "G:\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
w.start()
File "G:\Anaconda3\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "G:\Anaconda3\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "G:\Anaconda3\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "G:\Anaconda3\lib\multiprocessing\popen_spawn_win32.py", line 65, in init
reduction.dump(process_obj, to_child)
File "G:\Anaconda3\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'ImageListEx.init..'

感谢您的分享！
请问训练不收敛的表现是怎么样的呢？
每个网络模型都有可能出现不收敛的问题吗？
在70-80个epoch之后，LBnet的loss几乎不再下降，recog_acc也稳定在80左右，是否每个网络需要的收敛迭代次数不同？
期待您的答复，再次表示感谢