I have tried many times to reproduce the tutorials in Fastai on my own but it usually ends up in some frustrating error message, I love this Library but I have not been able to run anything with it. Please can anyone help guide me just in case I am doing something wrong. I have a Windows 10, with CUDA 10.0 on a GEFORCE GTX. below is the error message I keep getting
on running:
learn = cnn_learner(data, models.resnet18, metrics=accuracy)
learn.fit_one_cycle(1,1e-2)
learn.save(‘mini_train’)
RuntimeError Traceback (most recent call last)
in
----> 1 learn = cnn_learner(data, models.resnet18, metrics=accuracy)
2 learn.fit_one_cycle(1,1e-2)
3 learn.save(‘mini_train’)
D:\makin\lib\site-packages\fastai\vision\learner.py in cnn_learner(data, base_arch, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, init, concat_pool, **kwargs)
96 model = create_cnn_model(base_arch, data.c, cut, pretrained, lin_ftrs, ps=ps, custom_head=custom_head,
97 split_on=split_on, bn_final=bn_final, concat_pool=concat_pool)
—> 98 learn = Learner(data, model, **kwargs)
99 learn.split(split_on or meta[‘split’])
100 if pretrained: learn.freeze()
in init(self, data, model, opt_func, loss_func, metrics, true_wd, bn_wd, wd, train_bn, path, model_dir, callback_fns, callbacks, layer_groups, add_time, silent)
D:\makin\lib\site-packages\fastai\basic_train.py in post_init(self)
164 self.path = Path(ifnone(self.path, self.data.path))
165 (self.path/self.model_dir).mkdir(parents=True, exist_ok=True)
–> 166 self.model = self.model.to(self.data.device)
167 self.loss_func = self.loss_func or self.data.loss_func
168 self.metrics=listify(self.metrics)
D:\makin\lib\site-packages\torch\nn\modules\module.py in to(self, *args, **kwargs)
384 return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
385
–> 386 return self._apply(convert)
387
388 def register_backward_hook(self, hook):
D:\makin\lib\site-packages\torch\nn\modules\module.py in _apply(self, fn)
191 def _apply(self, fn):
192 for module in self.children():
–> 193 module._apply(fn)
194
195 for param in self._parameters.values():
D:\makin\lib\site-packages\torch\nn\modules\module.py in _apply(self, fn)
191 def _apply(self, fn):
192 for module in self.children():
–> 193 module._apply(fn)
194
195 for param in self._parameters.values():
D:\makin\lib\site-packages\torch\nn\modules\module.py in _apply(self, fn)
197 # Tensors stored in modules are graph leaves, and we don’t
198 # want to create copy nodes, so we have to unpack the data.
–> 199 param.data = fn(param.data)
200 if param._grad is not None:
201 param._grad.data = fn(param._grad.data)
D:\makin\lib\site-packages\torch\nn\modules\module.py in convert(t)
382
383 def convert(t):
–> 384 return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
385
386 return self._apply(convert)
D:\makin\lib\site-packages\torch\cuda_init_.py in _lazy_init()
161 "Cannot re-initialize CUDA in forked subprocess. " + msg)
162 _check_driver()
–> 163 torch._C._cuda_init()
164 _cudart = _load_cudart()
165 _cudart.cudaGetErrorName.restype = ctypes.c_char_p
RuntimeError: CUDA error: unknown error
Another error here on running:
data.show_batch(rows=3, figsize=(4,4))
BrokenPipeError Traceback (most recent call last)
in
----> 1 data.show_batch(rows=3, figsize=(4,4), num_workers=0)
D:\makin\lib\site-packages\fastai\basic_data.py in show_batch(self, rows, ds_type, reverse, **kwargs)
183 def show_batch(self, rows:int=5, ds_type:DatasetType=DatasetType.Train, reverse:bool=False, **kwargs)->None:
184 “Show a batch of data in ds_type
on a few rows
.”
–> 185 x,y = self.one_batch(ds_type, True, True)
186 if reverse: x,y = x.flip(0),y.flip(0)
187 n_items = rows **2 if self.train_ds.x._square_show else rows
D:\makin\lib\site-packages\fastai\basic_data.py in one_batch(self, ds_type, detach, denorm, cpu)
166 w = self.num_workers
167 self.num_workers = 0
–> 168 try: x,y = next(iter(dl))
169 finally: self.num_workers = w
170 if detach: x,y = to_detach(x,cpu=cpu),to_detach(y,cpu=cpu)
D:\makin\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
D:\makin\lib\site-packages\torch\utils\data\dataloader.py in iter(self)
191
192 def iter(self):
–> 193 return _DataLoaderIter(self)
194
195 def len(self):
D:\makin\lib\site-packages\torch\utils\data\dataloader.py in init(self, loader)
467 # before it starts, and del tries to join but will get:
468 # AssertionError: can only join a started process.
–> 469 w.start()
470 self.index_queues.append(index_queue)
471 self.workers.append(w)
D:\makin\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
D:\makin\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):
D:\makin\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):
D:\makin\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)
D:\makin\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