SOLVED (in reply)
Hi there,
I am trying to segment my images. I made masks for them that only have two pixel classes with values 0 and 1 (saved in PNG format).
To get started, I just decided to use the tutorial for camvid_tiny segmentation https://github.com/fastai/fastai/blob/master/nbs/23_tutorial.vision.ipynb
Just repeating all the code from the tutorial (except of bs and resize)
fnames = get_image_files(path/'images')
def label_func(x): return path/'masks'/f'{x.stem}_P{x.suffix}'
codes = np.loadtxt(path/'labels.txt', dtype=str)
dls = SegmentationDataLoaders.from_label_func(path,
fnames,
label_func,
codes=codes,
bs=2,
item_tfms=[Resize(144)],
num_workers=0)
x,y = dls.one_batch()
dls.show_batch()
here I see my images with masks. Batches seems OK.
Learner learn = unet_learner(dls, resnet34) is created without errors and then I get the error on learn.fine_tune(8)
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-27-f067e6d6d342> in <module>
1 learn = unet_learner(dls, resnet34)
----> 2 learn.fine_tune(8)
~\Anaconda3\lib\site-packages\fastcore\utils.py in _f(*args, **kwargs)
470 init_args.update(log)
471 setattr(inst, 'init_args', init_args)
--> 472 return inst if to_return else f(*args, **kwargs)
473 return _f
474
~\Anaconda3\lib\site-packages\fastai\callback\schedule.py in fine_tune(self, epochs, base_lr, freeze_epochs, lr_mult, pct_start, div, **kwargs)
159 "Fine tune with `freeze` for `freeze_epochs` then with `unfreeze` from `epochs` using discriminative LR"
160 self.freeze()
--> 161 self.fit_one_cycle(freeze_epochs, slice(base_lr), pct_start=0.99, **kwargs)
162 base_lr /= 2
163 self.unfreeze()
~\Anaconda3\lib\site-packages\fastcore\utils.py in _f(*args, **kwargs)
470 init_args.update(log)
471 setattr(inst, 'init_args', init_args)
--> 472 return inst if to_return else f(*args, **kwargs)
473 return _f
474
~\Anaconda3\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)
111 scheds = {'lr': combined_cos(pct_start, lr_max/div, lr_max, lr_max/div_final),
112 'mom': combined_cos(pct_start, *(self.moms if moms is None else moms))}
--> 113 self.fit(n_epoch, cbs=ParamScheduler(scheds)+L(cbs), reset_opt=reset_opt, wd=wd)
114
115 # Cell
~\Anaconda3\lib\site-packages\fastcore\utils.py in _f(*args, **kwargs)
470 init_args.update(log)
471 setattr(inst, 'init_args', init_args)
--> 472 return inst if to_return else f(*args, **kwargs)
473 return _f
474
~\Anaconda3\lib\site-packages\fastai\learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
205 self.opt.set_hypers(lr=self.lr if lr is None else lr)
206 self.n_epoch,self.loss = n_epoch,tensor(0.)
--> 207 self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
208
209 def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None
~\Anaconda3\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()
~\Anaconda3\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 @log_args(but='cbs')
~\Anaconda3\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()
~\Anaconda3\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
~\Anaconda3\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):
~\Anaconda3\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()
~\Anaconda3\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):
~\Anaconda3\lib\site-packages\fastai\learner.py in one_batch(self, i, b)
177 self.iter = i
178 self._split(b)
--> 179 self._with_events(self._do_one_batch, 'batch', CancelBatchException)
180
181 def _do_epoch_train(self):
~\Anaconda3\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()
~\Anaconda3\lib\site-packages\fastai\learner.py in _do_one_batch(self)
164 self.pred = self.model(*self.xb)
165 self('after_pred')
--> 166 if len(self.yb): self.loss = self.loss_func(self.pred, *self.yb)
167 self('after_loss')
168 if not self.training or not len(self.yb): return
~\Anaconda3\lib\site-packages\fastai\layers.py in __call__(self, inp, targ, **kwargs)
295 if targ.dtype in [torch.int8, torch.int16, torch.int32]: targ = targ.long()
296 if self.flatten: inp = inp.view(-1,inp.shape[-1]) if self.is_2d else inp.view(-1)
--> 297 return self.func.__call__(inp, targ.view(-1) if self.flatten else targ, **kwargs)
298
299 # Cell
~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~\Anaconda3\lib\site-packages\torch\nn\modules\loss.py in forward(self, input, target)
946 def forward(self, input: Tensor, target: Tensor) -> Tensor:
947 return F.cross_entropy(input, target, weight=self.weight,
--> 948 ignore_index=self.ignore_index, reduction=self.reduction)
949
950
~\Anaconda3\lib\site-packages\torch\nn\functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
2420 if size_average is not None or reduce is not None:
2421 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2422 return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
2423
2424
~\Anaconda3\lib\site-packages\torch\nn\functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
2216 .format(input.size(0), target.size(0)))
2217 if dim == 2:
-> 2218 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
2219 elif dim == 4:
2220 ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: cuda runtime error (710) : device-side assert triggered at C:/cb/pytorch_1000000000000/work/aten/src\THCUNN/generic/ClassNLLCriterion.cu:118
I repeated the camvid tutorial on my computer, it works fine, there are no errors, and an error appears with my data.
I noticed that after I create a dataloaders with batches and execute the following code.
x,y = dls.one_batch()
dls.show_batch()
y[0],y[0].min(),y[0].max()
Then the values in the masks are 0 and 255 instead of 0 and 1. Maybe this is the problem? But I don’t understand why the values in masks change after batch creation. Before creating batches, they are equal to 0 or 1.
fastai version - 2.0.9
Update: I made test mask with 0,1,2 pixel values just in case. Before SegmentationDataLoaders it looks like this
And after DataLoaders it looks like normalization happened…
In camvid dataset all masks looks OK like this
At the same time, I compared camvid masks files with masks for my data and found no significant difference between them. Both masks are 8 bit grayscale