I had not used fastai for a while, I recently updated to latest version. I am using the following code which seems pretty standard for a simple tabular classification problem. I am using everything straight from the fastai tabular tutorial, I don’t do any fancy loss or anything.
procs = [Categorify, FillMissing, Normalize]
dls = TabularDataLoaders.from_df(df_final, procs=procs, cat_names=cat_names, cont_names=cont_names,
y_names="Churn", y_block=CategoryBlock(), valid_idx=df_notshared[test_mask].index.tolist(), bs=1024, n_jobs=8)
learn = tabular_learner(dls, metrics=[accuracy, Precision, Recall])
learn = learn.to_fp16()
learn.fit_one_cycle(10)
But then I get the following error when running this:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-10-184a41e6b7e2> in <module>
----> 1 learn.fit_one_cycle(10)
c:\work\ml\fastai\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
c:\work\ml\fastai\fastai\learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
216 self.opt.set_hypers(lr=self.lr if lr is None else lr)
217 self.n_epoch = n_epoch
--> 218 self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
219
220 def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None
c:\work\ml\fastai\fastai\learner.py in _with_events(self, f, event_type, ex, final)
158
159 def _with_events(self, f, event_type, ex, final=noop):
--> 160 try: self(f'before_{event_type}'); f()
161 except ex: self(f'after_cancel_{event_type}')
162 self(f'after_{event_type}'); final()
c:\work\ml\fastai\fastai\learner.py in _do_fit(self)
207 for epoch in range(self.n_epoch):
208 self.epoch=epoch
--> 209 self._with_events(self._do_epoch, 'epoch', CancelEpochException)
210
211 def fit(self, n_epoch, lr=None, wd=None, cbs=None, reset_opt=False):
c:\work\ml\fastai\fastai\learner.py in _with_events(self, f, event_type, ex, final)
158
159 def _with_events(self, f, event_type, ex, final=noop):
--> 160 try: self(f'before_{event_type}'); f()
161 except ex: self(f'after_cancel_{event_type}')
162 self(f'after_{event_type}'); final()
c:\work\ml\fastai\fastai\learner.py in _do_epoch(self)
201
202 def _do_epoch(self):
--> 203 self._do_epoch_train()
204 self._do_epoch_validate()
205
c:\work\ml\fastai\fastai\learner.py in _do_epoch_train(self)
193 def _do_epoch_train(self):
194 self.dl = self.dls.train
--> 195 self._with_events(self.all_batches, 'train', CancelTrainException)
196
197 def _do_epoch_validate(self, ds_idx=1, dl=None):
c:\work\ml\fastai\fastai\learner.py in _with_events(self, f, event_type, ex, final)
158
159 def _with_events(self, f, event_type, ex, final=noop):
--> 160 try: self(f'before_{event_type}'); f()
161 except ex: self(f'after_cancel_{event_type}')
162 self(f'after_{event_type}'); final()
c:\work\ml\fastai\fastai\learner.py in all_batches(self)
164 def all_batches(self):
165 self.n_iter = len(self.dl)
--> 166 for o in enumerate(self.dl): self.one_batch(*o)
167
168 def _do_one_batch(self):
c:\work\ml\fastai\fastai\learner.py in one_batch(self, i, b)
189 b = self._set_device(b)
190 self._split(b)
--> 191 self._with_events(self._do_one_batch, 'batch', CancelBatchException)
192
193 def _do_epoch_train(self):
c:\work\ml\fastai\fastai\learner.py in _with_events(self, f, event_type, ex, final)
158
159 def _with_events(self, f, event_type, ex, final=noop):
--> 160 try: self(f'before_{event_type}'); f()
161 except ex: self(f'after_cancel_{event_type}')
162 self(f'after_{event_type}'); final()
c:\work\ml\fastai\fastai\learner.py in _do_one_batch(self)
170 self('after_pred')
171 if len(self.yb):
--> 172 self.loss_grad = self.loss_func(self.pred, *self.yb)
173 self.loss = self.loss_grad.clone()
174 self('after_loss')
c:\work\ml\fastai\fastai\losses.py in __call__(self, inp, targ, **kwargs)
33 if targ.dtype in [torch.int8, torch.int16, torch.int32]: targ = targ.long()
34 if self.flatten: inp = inp.view(-1,inp.shape[-1]) if self.is_2d else inp.view(-1)
---> 35 return self.func.__call__(inp, targ.view(-1) if self.flatten else targ, **kwargs)
36
37 # Cell
~\miniconda3\envs\fastai\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
~\miniconda3\envs\fastai\lib\site-packages\torch\nn\modules\loss.py in forward(self, input, target)
1045 def forward(self, input: Tensor, target: Tensor) -> Tensor:
1046 assert self.weight is None or isinstance(self.weight, Tensor)
-> 1047 return F.cross_entropy(input, target, weight=self.weight,
1048 ignore_index=self.ignore_index, reduction=self.reduction)
1049
~\miniconda3\envs\fastai\lib\site-packages\torch\nn\functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
2678 """
2679 if has_torch_function_variadic(input, target):
-> 2680 return handle_torch_function(
2681 cross_entropy,
2682 (input, target),
~\miniconda3\envs\fastai\lib\site-packages\torch\overrides.py in handle_torch_function(public_api, relevant_args, *args, **kwargs)
1200 # Use `public_api` instead of `implementation` so __torch_function__
1201 # implementations can do equality/identity comparisons.
-> 1202 result = overloaded_arg.__torch_function__(public_api, types, args, kwargs)
1203
1204 if result is not NotImplemented:
c:\work\ml\fastai\fastai\torch_core.py in __torch_function__(self, func, types, args, kwargs)
330 convert=False
331 if _torch_handled(args, self._opt, func): convert,types = type(self),(torch.Tensor,)
--> 332 res = super().__torch_function__(func, types, args=args, kwargs=kwargs)
333 if convert: res = convert(res)
334 if isinstance(res, TensorBase): res.set_meta(self, as_copy=True)
~\miniconda3\envs\fastai\lib\site-packages\torch\tensor.py in __torch_function__(cls, func, types, args, kwargs)
960
961 with _C.DisableTorchFunction():
--> 962 ret = func(*args, **kwargs)
963 return _convert(ret, cls)
964
~\miniconda3\envs\fastai\lib\site-packages\torch\nn\functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
2691 if size_average is not None or reduce is not None:
2692 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2693 return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
2694
2695
~\miniconda3\envs\fastai\lib\site-packages\torch\nn\functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
2386 )
2387 if dim == 2:
-> 2388 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
2389 elif dim == 4:
2390 ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: expected scalar type Long but found Float