An update on this. I am not quite sure if this should be the proper place to comment this. If you think is necessary I will open another topis.
I am trying to reformulate the whole pipeline to expect multicategory inputs. As @morgan did, I tried first to train the single models with both class imbalance weights and multicategory.
The thing is, I can train the visual model without an issue with something like:
get_x = lambda x:path/f'{x[0]}'
#get_y=ColReader('Label')
def get_y(r): return r[1].split(' ') # This is te column where the labels are (4 of them)
batch_tfms = aug_transforms(flip_vert=False,do_flip=False, max_lighting=0.1, max_zoom=1.05, max_warp=0.)
#blocks = (ImageBlock(cls=PILDicom), CategoryBlock(vocab=[0,1]))
im_db_m = DataBlock(blocks = (ImageBlock, MultiCategoryBlock),
get_x = get_x,
get_y =get_y,
#get_y = ColReader('Label'),
#item_tfms = RandomResizedCrop(128, min_scale=0.35),
#batch_tfms=Normalize.from_stats(*imagenet_stats)
splitter = splitter,
item_tfms = Resize(512),
batch_tfms = batch_tfms
)
vis_dl_m = im_db.dataloaders(train_df_ready, bs=8)
vis_learn_m = cnn_learner(vis_dl_m, resnet34, metrics=accuracy_multi, pretrained=True)
vis_dl_m.loss_func = BCEWithLogitsLossFlat(weight=class_weights)
being class_weights = tensor([11.3539, 1.0000, 5.8010, 5.1732], device='cuda')
Here I have to mention that I have a dataset with 4 single classes but I would like to train the model to expect merged labels in the future, that’s the reason for the multicategory. If you think a better approach should be performed, please, tell me and stop reading 
So, fot the tabular_learner I have issues. I hot encoded the variables as explained here so I have a dataset with 4 more columns with my labels and True/False. If I try to train like:
y_names=['Label1', 'Label2', 'Label3', 'Label4']
to = TabularPandas(df_multi, procs, cat_names, cont_names,
y_names=y_names,
y_block=MultiCategoryBlock(encoded=True, vocab=y_names),
splits=splits)
tab_dl_m = to.dataloaders(bs=8)
tab_learn_m = tabular_learner(tab_dl_m, metrics=accuracy_multi)
tab_learn_m.loss_func = BCEWithLogitsLossFlat(weight=class_weights)
tab_learn_m.fit_one_cycle(3)
A dimension error occurs:
epoch train_loss valid_loss accuracy_multi time
0 0.000000 00:00
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-277-14422a88807c> in <module>
----> 1 tab_learn_m.fit_one_cycle(3)
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/fastcore/utils.py in _f(*args, **kwargs)
452 init_args.update(log)
453 setattr(inst, 'init_args', init_args)
--> 454 return inst if to_return else f(*args, **kwargs)
455 return _f
456
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastcore/utils.py in _f(*args, **kwargs)
452 init_args.update(log)
453 setattr(inst, 'init_args', init_args)
--> 454 return inst if to_return else f(*args, **kwargs)
455 return _f
456
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
202 self.opt.set_hypers(lr=self.lr if lr is None else lr)
203 self.n_epoch,self.loss = n_epoch,tensor(0.)
--> 204 self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
205
206 def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_fit(self)
192 for epoch in range(self.n_epoch):
193 self.epoch=epoch
--> 194 self._with_events(self._do_epoch, 'epoch', CancelEpochException)
195
196 @log_args(but='cbs')
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_epoch(self)
186
187 def _do_epoch(self):
--> 188 self._do_epoch_train()
189 self._do_epoch_validate()
190
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_epoch_train(self)
178 def _do_epoch_train(self):
179 self.dl = self.dls.train
--> 180 self._with_events(self.all_batches, 'train', CancelTrainException)
181
182 def _do_epoch_validate(self, ds_idx=1, dl=None):
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in one_batch(self, i, b)
174 self.iter = i
175 self._split(b)
--> 176 self._with_events(self._do_one_batch, 'batch', CancelBatchException)
177
178 def _do_epoch_train(self):
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_one_batch(self)
164 self.pred = self.model(*self.xb); self('after_pred')
165 if len(self.yb) == 0: return
--> 166 self.loss = self.loss_func(self.pred, *self.yb); self('after_loss')
167 if not self.training: return
168 self('before_backward')
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
626
627 def forward(self, input: Tensor, target: Tensor) -> Tensor:
--> 628 return F.binary_cross_entropy_with_logits(input, target,
629 self.weight,
630 pos_weight=self.pos_weight,
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/torch/nn/functional.py in binary_cross_entropy_with_logits(input, target, weight, size_average, reduce, reduction, pos_weight)
2538 raise ValueError("Target size ({}) must be the same as input size ({})".format(target.size(), input.size()))
2539
-> 2540 return torch.binary_cross_entropy_with_logits(input, target, weight, pos_weight, reduction_enum)
2541
2542
RuntimeError: The size of tensor a (32) must match the size of tensor b (4) at non-singleton dimension 0
So, somehow tabular learner loss expects a 32 weights tensor. Tried to add a 32 tensor in the class weights filling the rest of values with 0 or with 1 but both options give me a similar dimension error. However this error appears at the end of the epoch:
epoch train_loss valid_loss accuracy_multi time
0 0.586030 0.579553 0.861255 00:15
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-288-14422a88807c> in <module>
----> 1 tab_learn_m.fit_one_cycle(3)
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/fastcore/utils.py in _f(*args, **kwargs)
452 init_args.update(log)
453 setattr(inst, 'init_args', init_args)
--> 454 return inst if to_return else f(*args, **kwargs)
455 return _f
456
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastcore/utils.py in _f(*args, **kwargs)
452 init_args.update(log)
453 setattr(inst, 'init_args', init_args)
--> 454 return inst if to_return else f(*args, **kwargs)
455 return _f
456
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
202 self.opt.set_hypers(lr=self.lr if lr is None else lr)
203 self.n_epoch,self.loss = n_epoch,tensor(0.)
--> 204 self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
205
206 def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_fit(self)
192 for epoch in range(self.n_epoch):
193 self.epoch=epoch
--> 194 self._with_events(self._do_epoch, 'epoch', CancelEpochException)
195
196 @log_args(but='cbs')
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_epoch(self)
187 def _do_epoch(self):
188 self._do_epoch_train()
--> 189 self._do_epoch_validate()
190
191 def _do_fit(self):
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_epoch_validate(self, ds_idx, dl)
183 if dl is None: dl = self.dls[ds_idx]
184 self.dl = dl;
--> 185 with torch.no_grad(): self._with_events(self.all_batches, 'validate', CancelValidException)
186
187 def _do_epoch(self):
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in one_batch(self, i, b)
174 self.iter = i
175 self._split(b)
--> 176 self._with_events(self._do_one_batch, 'batch', CancelBatchException)
177
178 def _do_epoch_train(self):
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/fastai/learner.py in _do_one_batch(self)
164 self.pred = self.model(*self.xb); self('after_pred')
165 if len(self.yb) == 0: return
--> 166 self.loss = self.loss_func(self.pred, *self.yb); self('after_loss')
167 if not self.training: return
168 self('before_backward')
~/anaconda3/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/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/envs/fastai2/lib/python3.8/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
626
627 def forward(self, input: Tensor, target: Tensor) -> Tensor:
--> 628 return F.binary_cross_entropy_with_logits(input, target,
629 self.weight,
630 pos_weight=self.pos_weight,
~/anaconda3/envs/fastai2/lib/python3.8/site-packages/torch/nn/functional.py in binary_cross_entropy_with_logits(input, target, weight, size_average, reduce, reduction, pos_weight)
2538 raise ValueError("Target size ({}) must be the same as input size ({})".format(target.size(), input.size()))
2539
-> 2540 return torch.binary_cross_entropy_with_logits(input, target, weight, pos_weight, reduction_enum)
2541
2542
RuntimeError: The size of tensor a (4) must match the size of tensor b (32) at non-singleton dimension 0
Sadly, multi_model expect the same as tabular_learner so I am kind of stuck. Any ideas why this is happening?