I’ve encountered a problem while running the 01_intro code locally in Visual Code Studio:
path = untar_data(URLs.CAMVID_TINY)
dls = SegmentationDataLoaders.from_label_func(
path, bs=8, fnames = get_image_files(path/"images"),
label_func = lambda o: path/'labels'/f'{o.stem}_P{o.suffix}',
codes = np.loadtxt(path/'codes.txt', dtype=str)
)
print(path)
learn = unet_learner(dls, resnet34)
learn.fine_tune(8)
I get the following error that does NOT happen in paperspace:
PicklingError Traceback (most recent call last)
<ipython-input-22-60c49369e175> in <module>
7 print(path)
8 learn = unet_learner(dls, resnet34)
----> 9 learn.fine_tune(8)
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\callback\schedule.py in fine_tune(self, epochs, base_lr, freeze_epochs, lr_mult, pct_start, div, **kwargs)
155 "Fine tune with `freeze` for `freeze_epochs` then with `unfreeze` from `epochs` using discriminative LR"
156 self.freeze()
--> 157 self.fit_one_cycle(freeze_epochs, slice(base_lr), pct_start=0.99, **kwargs)
158 base_lr /= 2
159 self.unfreeze()
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\callback\schedule.py in fit_one_cycle(self, n_epoch, lr_max, div, div_final, pct_start, wd, moms, cbs, reset_opt)
110 scheds = {'lr': combined_cos(pct_start, lr_max/div, lr_max, lr_max/div_final),
111 'mom': combined_cos(pct_start, *(self.moms if moms is None else moms))}
--> 112 self.fit(n_epoch, cbs=ParamScheduler(scheds)+L(cbs), reset_opt=reset_opt, wd=wd)
113
114 # Cell
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
204 self.opt.set_hypers(lr=self.lr if lr is None else lr)
205 self.n_epoch = n_epoch
--> 206 self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
207
208 def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in _with_events(self, f, event_type, ex, final)
153
154 def _with_events(self, f, event_type, ex, final=noop):
--> 155 try: self(f'before_{event_type}') ;f()
156 except ex: self(f'after_cancel_{event_type}')
157 finally: self(f'after_{event_type}') ;final()
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in _do_fit(self)
195 for epoch in range(self.n_epoch):
196 self.epoch=epoch
--> 197 self._with_events(self._do_epoch, 'epoch', CancelEpochException)
198
199 def fit(self, n_epoch, lr=None, wd=None, cbs=None, reset_opt=False):
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in _with_events(self, f, event_type, ex, final)
153
154 def _with_events(self, f, event_type, ex, final=noop):
--> 155 try: self(f'before_{event_type}') ;f()
156 except ex: self(f'after_cancel_{event_type}')
157 finally: self(f'after_{event_type}') ;final()
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in _do_epoch(self)
189
190 def _do_epoch(self):
--> 191 self._do_epoch_train()
192 self._do_epoch_validate()
193
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in _do_epoch_train(self)
181 def _do_epoch_train(self):
182 self.dl = self.dls.train
--> 183 self._with_events(self.all_batches, 'train', CancelTrainException)
184
185 def _do_epoch_validate(self, ds_idx=1, dl=None):
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in _with_events(self, f, event_type, ex, final)
153
154 def _with_events(self, f, event_type, ex, final=noop):
--> 155 try: self(f'before_{event_type}') ;f()
156 except ex: self(f'after_cancel_{event_type}')
157 finally: self(f'after_{event_type}') ;final()
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\learner.py in all_batches(self)
159 def all_batches(self):
160 self.n_iter = len(self.dl)
--> 161 for o in enumerate(self.dl): self.one_batch(*o)
162
163 def _do_one_batch(self):
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\fastai\data\load.py in __iter__(self)
99 self.before_iter()
100 self.__idxs=self.get_idxs() # called in context of main process (not workers/subprocesses)
--> 101 for b in _loaders[self.fake_l.num_workers==0](self.fake_l):
102 if self.device is not None: b = to_device(b, self.device)
103 yield self.after_batch(b)
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py in __init__(self, loader)
799 # before it starts, and __del__ tries to join but will get:
800 # AssertionError: can only join a started process.
--> 801 w.start()
802 self._index_queues.append(index_queue)
803 self._workers.append(w)
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\multiprocessing\process.py in start(self)
103 'daemonic processes are not allowed to have children'
104 _cleanup()
--> 105 self._popen = self._Popen(self)
106 self._sentinel = self._popen.sentinel
107 _children.add(self)
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\multiprocessing\context.py in _Popen(process_obj)
221 @staticmethod
222 def _Popen(process_obj):
--> 223 return _default_context.get_context().Process._Popen(process_obj)
224
225 class DefaultContext(BaseContext):
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\multiprocessing\context.py in _Popen(process_obj)
320 def _Popen(process_obj):
321 from .popen_spawn_win32 import Popen
--> 322 return Popen(process_obj)
323
324 class SpawnContext(BaseContext):
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\multiprocessing\popen_spawn_win32.py in __init__(self, process_obj)
63 try:
64 reduction.dump(prep_data, to_child)
---> 65 reduction.dump(process_obj, to_child)
66 finally:
67 set_spawning_popen(None)
C:\Users\jbiss\AppData\Local\Programs\Python\Python36\lib\multiprocessing\reduction.py in dump(obj, file, protocol)
58 def dump(obj, file, protocol=None):
59 '''Replacement for pickle.dump() using ForkingPickler.'''
---> 60 ForkingPickler(file, protocol).dump(obj)
61
62 #
PicklingError: Can't pickle <function <lambda> at 0x00000288834C0F28>: attribute lookup <lambda> on __main__ failed
Pickle Error with resnext101_32x4d Pretrained models discusses the same problem and provides an answer that doesn’t seem to work. Neither unet_learner
nor Learner.fine_tune
provides purge as a parameter.
It seems that this error is beyond my control and I do not know why it pops up locally. So, is there any advice as to how we can resolve these problems on our own, how to troubleshoot them?