=== Software ===
python : 3.7.6
fastai : 1.0.60
fastprogress : 0.2.2
torch : 1.4.0
torch cuda : 10.1
Hi all,
I’m just a beginner. I have a problem.
Problem: BrokenPipeError: [Errno 32] Broken pipe when it comes from 12th cell (In[12], jupyter notebook)
Error code:
learn.fit_one_cycle(6, lr, callbacks = [AccumulateStep(learn,n_acc)])
Code from In [12]:
scores, best_thrs = [],[]
for fold in range(nfolds):
print('fold: ', fold)
data = get_data(fold)
learn = unet_learner(data, models.resnet34, metrics=[dice])
learn.clip_grad(1.0);
set_BN_momentum(learn.model)
#fit the decoder part of the model keeping the encode frozen
lr = 1e-3
learn.fit_one_cycle(12, lr, callbacks = [AccumulateStep(learn,n_acc)])
#fit entire model with saving on the best epoch
learn.unfreeze()
learn.fit_one_cycle(12, slice(lr/80, lr/2), callbacks=[AccumulateStep(learn,n_acc)])
learn.save('fold'+str(fold));
#prediction on val and test sets
preds, ys = pred_with_flip(learn)
pt, _ = pred_with_flip(learn,DatasetType.Test)
if fold == 0: preds_test = pt
else: preds_test += pt
#convert predictions to byte type and save
preds_save = (preds*255.0).byte()
torch.save(preds_save, 'preds_fold'+str(fold)+'.pt')
np.save('items_fold'+str(fold), data.valid_ds.items)
#remove noise
preds[preds.view(preds.shape[0],-1).sum(-1) < noise_th,...] = 0.0
#optimal threshold
#The best way would be collecting all oof predictions followed by a single threshold
#calculation. However, it requres too much RAM for high image resolution
dices = []
thrs = np.arange(0.01, 1, 0.01)
for th in progress_bar(thrs):
preds_m = (preds>th).long()
dices.append(dice_overall(preds_m, ys).mean())
dices = np.array(dices)
scores.append(dices.max())
best_thrs.append(thrs[dices.argmax()])
if fold != nfolds-1: del preds, ys, preds_save
gc.collect()
torch.cuda.empty_cache()
preds_test /= nfolds
After running: BrokenPipeError Traceback (most recent call last)
BrokenPipeError Traceback (most recent call last)
<ipython-input-12-13acb8b35833> in <module>
10 #fit the decoder part of the model keeping the encode frozen
11 lr = 1e-3
---> 12 learn.fit_one_cycle(12, lr, callbacks = [AccumulateStep(learn,n_acc)])
13
14 #fit entire model with saving on the best epoch
~\anaconda3\lib\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)
21 callbacks.append(OneCycleScheduler(learn, max_lr, moms=moms, div_factor=div_factor, pct_start=pct_start,
22 final_div=final_div, tot_epochs=tot_epochs, start_epoch=start_epoch))
---> 23 learn.fit(cyc_len, max_lr, wd=wd, callbacks=callbacks)
24
25 def fit_fc(learn:Learner, tot_epochs:int=1, lr:float=defaults.lr, moms:Tuple[float,float]=(0.95,0.85), start_pct:float=0.72,
~\anaconda3\lib\site-packages\fastai\basic_train.py in fit(self, epochs, lr, wd, callbacks)
198 else: self.opt.lr,self.opt.wd = lr,wd
199 callbacks = [cb(self) for cb in self.callback_fns + listify(defaults.extra_callback_fns)] + listify(callbacks)
--> 200 fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
201
202 def create_opt(self, lr:Floats, wd:Floats=0.)->None:
~\anaconda3\lib\site-packages\fastai\basic_train.py in fit(epochs, learn, callbacks, metrics)
97 cb_handler.set_dl(learn.data.train_dl)
98 cb_handler.on_epoch_begin()
---> 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)
~\anaconda3\lib\site-packages\fastprogress\fastprogress.py in __iter__(self)
45 except Exception as e:
46 self.on_interrupt()
---> 47 raise e
48
49 def update(self, val):
~\anaconda3\lib\site-packages\fastprogress\fastprogress.py in __iter__(self)
39 if self.total != 0: self.update(0)
40 try:
---> 41 for i,o in enumerate(self.gen):
42 if i >= self.total: break
43 yield o
~\anaconda3\lib\site-packages\fastai\basic_data.py in __iter__(self)
73 def __iter__(self):
74 "Process and returns items from `DataLoader`."
---> 75 for b in self.dl: yield self.proc_batch(b)
76
77 @classmethod
~\anaconda3\lib\site-packages\torch\utils\data\dataloader.py in __iter__(self)
277 return _SingleProcessDataLoaderIter(self)
278 else:
--> 279 return _MultiProcessingDataLoaderIter(self)
280
281 @property
~\anaconda3\lib\site-packages\torch\utils\data\dataloader.py in __init__(self, loader)
717 # before it starts, and __del__ tries to join but will get:
718 # AssertionError: can only join a started process.
--> 719 w.start()
720 self._index_queues.append(index_queue)
721 self._workers.append(w)
~\anaconda3\lib\multiprocessing\process.py in start(self)
110 'daemonic processes are not allowed to have children'
111 _cleanup()
--> 112 self._popen = self._Popen(self)
113 self._sentinel = self._popen.sentinel
114 # Avoid a refcycle if the target function holds an indirect
~\anaconda3\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):
~\anaconda3\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):
~\anaconda3\lib\multiprocessing\popen_spawn_win32.py in __init__(self, process_obj)
87 try:
88 reduction.dump(prep_data, to_child)
---> 89 reduction.dump(process_obj, to_child)
90 finally:
91 set_spawning_popen(None)
~\anaconda3\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 #
BrokenPipeError: [Errno 32] Broken pipe
Source code: Hypercolumns pneumothorax fastai [0.831 LB] | Kaggle
Thanks all.