Hi everyone,
I am trying to train a model with a Resnet34 architecture in order to tackle a segmentation problem.
The dataset was collected for training an algorithm for classification regions of documents on text, picture and background areas. It contains 101 scanned images of various newspapers and magazines in Russian.
There are three classes: text area, picture area, background.
Pixels on the mask with color 255, 0, 0 (rgb, red color) correspond to picture area, pixels with color 0, 0, 255 (rgb, blue color) correspond to text area, all other pixels correspond to background (Images with background of different colors are in the dataset).
This is the way I use the Data Block API to produce a DataBunch:
src = (SegmentationItemList.from_folder(path)
.filter_by_func(is_not_mask)
.random_split_by_pct(0.2)
.label_from_func(get_image_mask, classes=codes))
data = (src.transform(get_transforms(), tfm_y=True, size=128)
.databunch(bs=bs)
.normalize(imagenet_stats))
This is the way I create a Learner:
acc_05 = partial(accuracy_thresh, thresh=0.5)
metrics=acc_05
wd=1e-2
learn = unet_learner(data, models.resnet34, metrics=metrics, wd=wd)
Unfortunately, when I run learn.lr_find() I got the following stack trace:
RuntimeError Traceback (most recent call last)
in ()
----> 1 learn.lr_find()
2 #learn.recorder.plot()
/usr/local/lib/python3.6/dist-packages/fastai/train.py in lr_find(learn, start_lr, end_lr, num_it, stop_div, **kwargs)
30 cb = LRFinder(learn, start_lr, end_lr, num_it, stop_div)
31 a = int(np.ceil(num_it/len(learn.data.train_dl)))
—> 32 learn.fit(a, start_lr, callbacks=[cb], **kwargs)
33
34 def to_fp16(learn:Learner, loss_scale:float=512., flat_master:bool=False)->Learner:
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks)
176 callbacks = [cb(self) for cb in self.callback_fns] + listify(callbacks)
177 fit(epochs, self.model, self.loss_func, opt=self.opt, data=self.data, metrics=self.metrics,
–> 178 callbacks=self.callbacks+callbacks)
179
180 def create_opt(self, lr:Floats, wd:Floats=0.)->None:
/usr/local/lib/python3.6/dist-packages/fastai/utils/mem.py in wrapper(*args, **kwargs)
83
84 try:
—> 85 return func(*args, **kwargs)
86 except Exception as e:
87 if “CUDA out of memory” in str(e) or tb_clear_frames==“1”:
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(epochs, model, loss_func, opt, data, callbacks, metrics)
98 except Exception as e:
99 exception = e
–> 100 raise e
101 finally: cb_handler.on_train_end(exception)
102
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(epochs, model, loss_func, opt, data, callbacks, metrics)
88 for xb,yb in progress_bar(data.train_dl, parent=pbar):
89 xb, yb = cb_handler.on_batch_begin(xb, yb)
—> 90 loss = loss_batch(model, xb, yb, loss_func, opt, cb_handler)
91 if cb_handler.on_batch_end(loss): break
92
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in loss_batch(model, xb, yb, loss_func, opt, cb_handler)
22
23 if not loss_func: return to_detach(out), yb[0].detach()
—> 24 loss = loss_func(out, *yb)
25
26 if opt is not None:
/usr/local/lib/python3.6/dist-packages/fastai/layers.py in call(self, input, target, **kwargs)
229 if self.floatify: target = target.float()
230 input = input.view(-1,input.shape[-1]) if self.is_2d else input.view(-1)
–> 231 return self.func.call(input, target.view(-1), **kwargs)
232
233 def CrossEntropyFlat(*args, axis:int=-1, **kwargs):
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in call(self, *input, **kwargs)
487 result = self._slow_forward(*input, **kwargs)
488 else:
–> 489 result = self.forward(*input, **kwargs)
490 for hook in self._forward_hooks.values():
491 hook_result = hook(self, input, result)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py in forward(self, input, target)
902 def forward(self, input, target):
903 return F.cross_entropy(input, target, weight=self.weight,
–> 904 ignore_index=self.ignore_index, reduction=self.reduction)
905
906
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
1968 if size_average is not None or reduce is not None:
1969 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 1970 return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
1971
1972
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
1788 .format(input.size(0), target.size(0)))
1789 if dim == 2:
-> 1790 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
1791 elif dim == 4:
1792 ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes’ failed. at /pytorch/aten/src/THNN/generic/ClassNLLCriterion.c:93
Any suggestion?
Matteo