I am getting the following runtime error while running the learn.TTA(is_test=True), the only thing I am doing different from the lesson2 notebook is loading the model using
learn.set_data(get_data(sz))
learn.load('256')
the stack trace
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-30-e855bad3db73> in <module>()
----> 1 log_preds, y = learn.TTA(is_test=True)
~/DL/fastai/courses/dl1/fastai/learner.py in TTA(self, n_aug, is_test)
148 dl1 = self.data.test_dl if is_test else self.data.val_dl
149 dl2 = self.data.test_aug_dl if is_test else self.data.aug_dl
--> 150 preds1,targs = predict_with_targs(self.model, dl1)
151 preds1 = [preds1]*math.ceil(n_aug/4)
152 preds2 = [predict_with_targs(self.model, dl2)[0] for i in range(n_aug)]
~/DL/fastai/courses/dl1/fastai/model.py in predict_with_targs(m, dl)
115 if hasattr(m, 'reset'): m.reset()
116 preda,targa = zip(*[(get_prediction(m(*VV(x))),y)
--> 117 for *x,y in iter(dl)])
118 return to_np(torch.cat(preda)), to_np(torch.cat(targa))
119
~/DL/fastai/courses/dl1/fastai/model.py in <listcomp>(.0)
114 m.eval()
115 if hasattr(m, 'reset'): m.reset()
--> 116 preda,targa = zip(*[(get_prediction(m(*VV(x))),y)
117 for *x,y in iter(dl)])
118 return to_np(torch.cat(preda)), to_np(torch.cat(targa))
~/DL/fastai/courses/dl1/fastai/dataset.py in __next__(self)
226 if self.i>=len(self.dl): raise StopIteration
227 self.i+=1
--> 228 return next(self.it)
229
230 @property
~/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py in __next__(self)
193 while True:
194 assert (not self.shutdown and self.batches_outstanding > 0)
--> 195 idx, batch = self.data_queue.get()
196 self.batches_outstanding -= 1
197 if idx != self.rcvd_idx:
~/anaconda3/lib/python3.6/multiprocessing/queues.py in get(self)
335 res = self._reader.recv_bytes()
336 # unserialize the data after having released the lock
--> 337 return _ForkingPickler.loads(res)
338
339 def put(self, obj):
~/anaconda3/lib/python3.6/site-packages/torch/multiprocessing/reductions.py in rebuild_storage_fd(cls, df, size)
68 fd = multiprocessing.reduction.rebuild_handle(df)
69 else:
---> 70 fd = df.detach()
71 try:
72 storage = storage_from_cache(cls, fd_id(fd))
~/anaconda3/lib/python3.6/multiprocessing/resource_sharer.py in detach(self)
56 '''Get the fd. This should only be called once.'''
57 with _resource_sharer.get_connection(self._id) as conn:
---> 58 return reduction.recv_handle(conn)
59
60
~/anaconda3/lib/python3.6/multiprocessing/reduction.py in recv_handle(conn)
180 '''Receive a handle over a local connection.'''
181 with socket.fromfd(conn.fileno(), socket.AF_UNIX, socket.SOCK_STREAM) as s:
--> 182 return recvfds(s, 1)[0]
183
184 def DupFd(fd):
~/anaconda3/lib/python3.6/multiprocessing/reduction.py in recvfds(sock, size)
159 if len(ancdata) != 1:
160 raise RuntimeError('received %d items of ancdata' %
--> 161 len(ancdata))
162 cmsg_level, cmsg_type, cmsg_data = ancdata[0]
163 if (cmsg_level == socket.SOL_SOCKET and
RuntimeError: received 0 items of ancdata
Thank–you, in advance
it solved the error I was having I will try to look at the code to find why so much file discriptors are kept opened. Thanks again.