Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.
TypeError: unsupported operand type(s) for *: 'TensorImage' and 'TensorMask' #3041
Description
Please confirm you have the latest versions of fastai, fastcore, fastscript, and nbdev prior to reporting a bug (delete one): YES
Describe the bug
With Fastai 2.1+ release I found errors that up to version 2.0.19 were not there.
I use a colab notebook for image segmentation. After FastAI 2.1 release, it no longer does work Dice Metric calculations.
To Reproduce
Steps to reproduce the behavior:
On Colab, run the camvid_tiny dataset w/ and w/o "metrics=Dice()" (see below). When running with metrics, error pops up. When running without "metrics=Dice()", the training is performed, but the metric is lacking.
!pip install -Uqq fastbook
import fastbook
fastbook.setup_book()
from fastbook import *
from fastai.basics import *
from fastai.vision.all import *
from fastai.vision.core import *
from fastai.vision.data import *
from fastai.data.all import *
path = untar_data(URLs.CAMVID_TINY)
dls = SegmentationDataLoaders.from_label_func(
path, bs=8, fnames = get_image_files(path/"images"),
label_func = lambda o: path/'labels'/f'{o.stem}_P{o.suffix}',
codes = np.loadtxt(path/'codes.txt', dtype=str)
)
learn = unet_learner(dls, resnet34, metrics=Dice())
learn.fine_tune(8)
=========================
Expected behavior
Expected the training to finish with a metrics. But it showed error message after the first epoch.
Error with full stack trace
TypeError Traceback (most recent call last)
<ipython-input-26-caae7391a127> in <module>()
----> 1 learn.fine_tune(16, freeze_epochs=4, base_lr=9e-4)
20 frames
/usr/local/lib/python3.6/dist-packages/fastai/callback/schedule.py in fine_tune(self, epochs, base_lr, freeze_epochs, lr_mult, pct_start, div, **kwargs)
155 "Fine tune with `freeze` for `freeze_epochs` then with `unfreeze` from `epochs` using discriminative LR"
156 self.freeze()
--> 157 self.fit_one_cycle(freeze_epochs, slice(base_lr), pct_start=0.99, **kwargs)
158 base_lr /= 2
159 self.unfreeze()
/usr/local/lib/python3.6/dist-packages/fastai/callback/schedule.py in fit_one_cycle(self, n_epoch, lr_max, div, div_final, pct_start, wd, moms, cbs, reset_opt)
110 scheds = {'lr': combined_cos(pct_start, lr_max/div, lr_max, lr_max/div_final),
111 'mom': combined_cos(pct_start, *(self.moms if moms is None else moms))}
--> 112 self.fit(n_epoch, cbs=ParamScheduler(scheds)+L(cbs), reset_opt=reset_opt, wd=wd)
113
114 # Cell
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
203 self.opt.set_hypers(lr=self.lr if lr is None else lr)
204 self.n_epoch = n_epoch
--> 205 self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
206
207 def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
152
153 def _with_events(self, f, event_type, ex, final=noop):
--> 154 try: self(f'before_{event_type}') ;f()
155 except ex: self(f'after_cancel_{event_type}')
156 finally: self(f'after_{event_type}') ;final()
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _do_fit(self)
194 for epoch in range(self.n_epoch):
195 self.epoch=epoch
--> 196 self._with_events(self._do_epoch, 'epoch', CancelEpochException)
197
198 def fit(self, n_epoch, lr=None, wd=None, cbs=None, reset_opt=False):
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
152
153 def _with_events(self, f, event_type, ex, final=noop):
--> 154 try: self(f'before_{event_type}') ;f()
155 except ex: self(f'after_cancel_{event_type}')
156 finally: self(f'after_{event_type}') ;final()
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _do_epoch(self)
189 def _do_epoch(self):
190 self._do_epoch_train()
--> 191 self._do_epoch_validate()
192
193 def _do_fit(self):
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _do_epoch_validate(self, ds_idx, dl)
185 if dl is None: dl = self.dls[ds_idx]
186 self.dl = dl
--> 187 with torch.no_grad(): self._with_events(self.all_batches, 'validate', CancelValidException)
188
189 def _do_epoch(self):
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
152
153 def _with_events(self, f, event_type, ex, final=noop):
--> 154 try: self(f'before_{event_type}') ;f()
155 except ex: self(f'after_cancel_{event_type}')
156 finally: self(f'after_{event_type}') ;final()
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in all_batches(self)
158 def all_batches(self):
159 self.n_iter = len(self.dl)
--> 160 for o in enumerate(self.dl): self.one_batch(*o)
161
162 def _do_one_batch(self):
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in one_batch(self, i, b)
176 self.iter = i
177 self._split(b)
--> 178 self._with_events(self._do_one_batch, 'batch', CancelBatchException)
179
180 def _do_epoch_train(self):
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
154 try: self(f'before_{event_type}') ;f()
155 except ex: self(f'after_cancel_{event_type}')
--> 156 finally: self(f'after_{event_type}') ;final()
157
158 def all_batches(self):
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in __call__(self, event_name)
130 def ordered_cbs(self, event): return [cb for cb in sort_by_run(self.cbs) if hasattr(cb, event)]
131
--> 132 def __call__(self, event_name): L(event_name).map(self._call_one)
133
134 def _call_one(self, event_name):
/usr/local/lib/python3.6/dist-packages/fastcore/foundation.py in map(self, f, gen, *args, **kwargs)
177 def range(cls, a, b=None, step=None): return cls(range_of(a, b=b, step=step))
178
--> 179 def map(self, f, *args, gen=False, **kwargs): return self._new(map_ex(self, f, *args, gen=gen, **kwargs))
180 def argwhere(self, f, negate=False, **kwargs): return self._new(argwhere(self, f, negate, **kwargs))
181 def filter(self, f=noop, negate=False, gen=False, **kwargs):
/usr/local/lib/python3.6/dist-packages/fastcore/basics.py in map_ex(iterable, f, gen, *args, **kwargs)
604 res = map(g, iterable)
605 if gen: return res
--> 606 return list(res)
607
608 # Cell
/usr/local/lib/python3.6/dist-packages/fastcore/basics.py in __call__(self, *args, **kwargs)
594 if isinstance(v,_Arg): kwargs[k] = args.pop(v.i)
595 fargs = [args[x.i] if isinstance(x, _Arg) else x for x in self.pargs] + args[self.maxi+1:]
--> 596 return self.func(*fargs, **kwargs)
597
598 # Cell
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in _call_one(self, event_name)
134 def _call_one(self, event_name):
135 assert hasattr(event, event_name), event_name
--> 136 [cb(event_name) for cb in sort_by_run(self.cbs)]
137
138 def _bn_bias_state(self, with_bias): return norm_bias_params(self.model, with_bias).map(self.opt.state)
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in <listcomp>(.0)
134 def _call_one(self, event_name):
135 assert hasattr(event, event_name), event_name
--> 136 [cb(event_name) for cb in sort_by_run(self.cbs)]
137
138 def _bn_bias_state(self, with_bias): return norm_bias_params(self.model, with_bias).map(self.opt.state)
/usr/local/lib/python3.6/dist-packages/fastai/callback/core.py in __call__(self, event_name)
42 (self.run_valid and not getattr(self, 'training', False)))
43 res = None
---> 44 if self.run and _run: res = getattr(self, event_name, noop)()
45 if event_name=='after_fit': self.run=True #Reset self.run to True at each end of fit
46 return res
/usr/local/lib/python3.6/dist-packages/fastai/learner.py in after_batch(self)
455 if len(self.yb) == 0: return
456 mets = self._train_mets if self.training else self._valid_mets
--> 457 for met in mets: met.accumulate(self.learn)
458 if not self.training: return
459 self.lrs.append(self.opt.hypers[-1]['lr'])
/usr/local/lib/python3.6/dist-packages/fastai/metrics.py in accumulate(self, learn)
346 def accumulate(self, learn):
347 pred,targ = flatten_check(learn.pred.argmax(dim=self.axis), learn.y)
--> 348 self.inter += (pred*targ).float().sum().item()
349 self.union += (pred+targ).float().sum().item()
350
TypeError: unsupported operand type(s) for *: 'TensorImage' and 'TensorMask'
Additional context
Pinning to older versions solves this particular problem.
!pip uninstall torch -y
# CUDA 10.1
!pip install torch==1.6.0+cu101 torchvision==0.7.0+cu101 -f https://download.pytorch.org/whl/torch_stable.html
!pip install fastai==2.0.19
!pip install fastcore==1.3.1
More can be found in
https://forums.fast.ai/t/a-walk-with-fastai2-vision-study-group-and-online-lectures-megathread/59929/1385