RuntimeError: expected dtype Float but got dtype Half

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-14-243bd3d406ab> in <module>
----> 1 learner.fine_tune(10)

/usr/local/lib/python3.8/dist-packages/fastcore/utils.py in _f(*args, **kwargs)
    429         init_args.update(log)
    430         setattr(inst, 'init_args', init_args)
--> 431         return inst if to_return else f(*args, **kwargs)
    432     return _f
    433

/usr/local/lib/python3.8/dist-packages/fastai2/callback/schedule.py in fine_tune(self, epochs, base_lr, freeze_epochs, lr_mult, pct_start, div, **kwargs)
    146     "Fine tune with `freeze` for `freeze_epochs` then with `unfreeze` from `epochs` using discriminative LR"
    147     self.freeze()
--> 148     self.fit_one_cycle(freeze_epochs, slice(base_lr), pct_start=0.99, **kwargs)
    149     base_lr /= 2
    150     self.unfreeze()

/usr/local/lib/python3.8/dist-packages/fastcore/utils.py in _f(*args, **kwargs)
    429         init_args.update(log)
    430         setattr(inst, 'init_args', init_args)
--> 431         return inst if to_return else f(*args, **kwargs)
    432     return _f
    433

/usr/local/lib/python3.8/dist-packages/fastai2/callback/schedule.py in fit_one_cycle(self, n_epoch, lr_max, div, div_final, pct_start, wd, moms, cbs, reset_opt)
     98     scheds = {'lr': combined_cos(pct_start, lr_max/div, lr_max, lr_max/div_final),
     99               'mom': combined_cos(pct_start, *(self.moms if moms is None else moms))}
--> 100     self.fit(n_epoch, cbs=ParamScheduler(scheds)+L(cbs), reset_opt=reset_opt, wd=wd)
    101
    102 # Cell

/usr/local/lib/python3.8/dist-packages/fastcore/utils.py in _f(*args, **kwargs)
    429         init_args.update(log)
    430         setattr(inst, 'init_args', init_args)
--> 431         return inst if to_return else f(*args, **kwargs)
    432     return _f
    433

/usr/local/lib/python3.8/dist-packages/fastai2/learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
    201                     try:
    202                         self.epoch=epoch;          self('begin_epoch')
--> 203                         self._do_epoch_train()
    204                         self._do_epoch_validate()
    205                     except CancelEpochException:   self('after_cancel_epoch')

/usr/local/lib/python3.8/dist-packages/fastai2/learner.py in _do_epoch_train(self)
    173         try:
    174             self.dl = self.dls.train;                        self('begin_train')
--> 175             self.all_batches()
    176         except CancelTrainException:                         self('after_cancel_train')
    177         finally:                                             self('after_train')

/usr/local/lib/python3.8/dist-packages/fastai2/learner.py in all_batches(self)
    151     def all_batches(self):
    152         self.n_iter = len(self.dl)
--> 153         for o in enumerate(self.dl): self.one_batch(*o)
    154
    155     def one_batch(self, i, b):

/usr/local/lib/python3.8/dist-packages/fastai2/learner.py in one_batch(self, i, b)
    157         try:
    158             self._split(b);                                  self('begin_batch')
--> 159             self.pred = self.model(*self.xb);                self('after_pred')
    160             if len(self.yb) == 0: return
    161             self.loss = self.loss_func(self.pred, *self.yb); self('after_loss')

/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    548             result = self._slow_forward(*input, **kwargs)
    549         else:
--> 550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
    552             hook_result = hook(self, input, result)

/usr/local/lib/python3.8/dist-packages/efficientnet_pytorch/model.py in forward(self, inputs)
    191         bs = inputs.size(0)
    192         # Convolution layers
--> 193         x = self.extract_features(inputs)
    194
    195         # Pooling and final linear layer

/usr/local/lib/python3.8/dist-packages/efficientnet_pytorch/model.py in extract_features(self, inputs)
    180             if drop_connect_rate:
    181                 drop_connect_rate *= float(idx) / len(self._blocks)
--> 182             x = block(x, drop_connect_rate=drop_connect_rate)
    183
    184         # Head

/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
--> 552             hook_result = hook(self, input, result)
    553             if hook_result is not None:
    554                 result = hook_result

~/Jupyter/manifold_mixup.py in hook_mixup(self, module, input, output)
    140         if not self.mixup_has_been_applied: # performs mixup
    141             output_dims = len(output.size())
--> 142             output = torch.lerp(output[self.shuffle], output, weight=unsqueeze(self.lam, n=output_dims-1))
    143             self.mixup_has_been_applied = True
    144             return output

RuntimeError: expected dtype Float but got dtype Half