Fastai: Expected input batch_size (17664) to match target batch_size (32).

[Cugtyt]

Describe the bug

Expected input batch_size (17664) to match target batch_size (32)
Provide your installation details

=== Software === 
python        : 3.7.3
fastai        : 1.0.51
fastprogress  : 0.1.20
torch         : 1.0.1.post2
nvidia driver : 410.79
torch cuda    : 8.0.61 / is available
torch cudnn   : 7102 / is enabled

=== Hardware === 
nvidia gpus   : 2
torch devices : 2
  - gpu0      : 11178MB | GeForce GTX 1080 Ti
  - gpu1      : 11178MB | GeForce GTX 1080 Ti

=== Environment === 
platform      : Linux-4.15.0-43-generic-x86_64-with-debian-stretch-sid
distro        : #46~16.04.1-Ubuntu SMP Fri Dec 7 13:31:08 UTC 2018
conda env     : /mnt/4A50ACA463E069FB/xxx/.env
python        : /mnt/4A50ACA463E069FB/xxx/.env/bin/python
sys.path      : /mnt/4A50ACA463E069FB/xxx
/mnt/4A50ACA463E069FB/xxx/.env/lib/python37.zip
/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7
/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/lib-dynload

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages
/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages/IPython/extensions
/home/lixin/.ipython

To Reproduce

data_lm = TextDataBunch.from_csv(path, 'train.csv', 
test='test.csv', text_cols='comment_text', label_cols='label', bs=32)

or

data_lm.save('data_lm.pkl')
data_lm = load_data(path, 'data_lm.pkl', bs=32)

then

learn = language_model_learner(data_lm, AWD_LSTM, drop_mult=0.3, path='.')
learn.lr_find()

The output is:
LR Finder is complete, type {learner_name}.recorder.plot() to see the graph.

---

ValueError Traceback (most recent call last)
in
----> 1 learn.lr_find()
2 # learn.recorder.plot(skip_end=15)

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages/fastai/train.py in lr_find(learn, start_lr, end_lr, num_it, stop_div, wd)
30 cb = LRFinder(learn, start_lr, end_lr, num_it, stop_div)
31 epochs = int(np.ceil(num_it/len(learn.data.train_dl)))
---> 32 learn.fit(epochs, start_lr, callbacks=[cb], wd=wd)
33
34 def to_fp16(learn:Learner, loss_scale:float=None, max_noskip:int=1000, dynamic:bool=True, clip:float=None,

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks)
194 callbacks = [cb(self) for cb in self.callback_fns] + listify(callbacks)
195 if defaults.extra_callbacks is not None: callbacks += defaults.extra_callbacks
--> 196 fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
197
198 def create_opt(self, lr:Floats, wd:Floats=0.)->None:

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages/fastai/basic_train.py in fit(epochs, learn, callbacks, metrics)
98 for xb,yb in progress_bar(learn.data.train_dl, parent=pbar):
99 xb, yb = cb_handler.on_batch_begin(xb, yb)
--> 100 loss = loss_batch(learn.model, xb, yb, learn.loss_func, learn.opt, cb_handler)
101 if cb_handler.on_batch_end(loss): break
102

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages/fastai/basic_train.py in loss_batch(model, xb, yb, loss_func, opt, cb_handler)
27
28 if not loss_func: return to_detach(out), yb[0].detach()
---> 29 loss = loss_func(out, *yb)
30
31 if opt is not None:

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages/fastai/layers.py in __call__(self, input, target, *kwargs)
265 if self.floatify: target = target.float()
266 input = input.view(-1,input.shape[-1]) if self.is_2d else input.view(-1)
--> 267 return self.func.__call__(input, target.view(-1), *kwargs)
268
269 def CrossEntropyFlat(args, axis:int=-1, *kwargs):

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-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)

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-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

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-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

/mnt/4A50ACA463E069FB/xxx/.env/lib/python3.7/site-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
1786 if input.size(0) != target.size(0):
1787 raise ValueError('Expected input batch_size ({}) to match target batch_size ({}).'
-> 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)

ValueError: Expected input batch_size (17664) to match target batch_size (32).

Expected behavior

It should work fine.
Screenshots

Additional context

the problem is also in
https://forums.fast.ai/t/v-1-0-50-lr-find-expected-input-batch-size-102512-to-match-target-batch-size-16/41721
If bs is not set, then the error will be out of memory

[sgugger]

You should use TextLMDataBunch. TextDataBunch shouldn't be used directly, it only implements base methods for the subclasses TextLMDataBunch and TextClasDataBunch.

[WarrenPretorius]

I am having a similar issue:
"ValueError: Expected input batch_size (8) to match target batch_size (1382400)."

I'm following the same procedure as presented in https://nbviewer.jupyter.org/github/fastai/course-v3/blob/master/nbs/dl1/lesson3-camvid.ipynb but in my case I'm trying to implement it using squeezenet1_1 instead of resnet34.

The only change I've made to the code is to replace
learn = unet_learner(data, models.resnet34, metrics=metrics, wd=wd)
with
learn = cnn_learner(data, models.squeezenet1_1, metrics=accuracy)

When it comes to executing lr_find() however, the following gets produced:

`ValueError Traceback (most recent call last)
in ()
----> 1 learn.lr_find()
2 learn.recorder.plot()

8 frames
/usr/local/lib/python3.6/dist-packages/fastai/train.py in lr_find(learn, start_lr, end_lr, num_it, stop_div, wd)
30 cb = LRFinder(learn, start_lr, end_lr, num_it, stop_div)
31 epochs = int(np.ceil(num_it/len(learn.data.train_dl)))
---> 32 learn.fit(epochs, start_lr, callbacks=[cb], wd=wd)
33
34 def to_fp16(learn:Learner, loss_scale:float=None, max_noskip:int=1000, dynamic:bool=True, clip:float=None,

/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks)
197 callbacks = [cb(self) for cb in self.callback_fns + listify(defaults.extra_callback_fns)] + listify(callbacks)
198 if defaults.extra_callbacks is not None: callbacks += defaults.extra_callbacks
--> 199 fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
200
201 def create_opt(self, lr:Floats, wd:Floats=0.)->None:

/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(epochs, learn, callbacks, metrics)
99 for xb,yb in progress_bar(learn.data.train_dl, parent=pbar):
100 xb, yb = cb_handler.on_batch_begin(xb, yb)
--> 101 loss = loss_batch(learn.model, xb, yb, learn.loss_func, learn.opt, cb_handler)
102 if cb_handler.on_batch_end(loss): break
103

/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in loss_batch(model, xb, yb, loss_func, opt, cb_handler)
28
29 if not loss_func: return to_detach(out), yb[0].detach()
---> 30 loss = loss_func(out, *yb)
31
32 if opt is not None:

/usr/local/lib/python3.6/dist-packages/fastai/layers.py in __call__(self, input, target, *kwargs)
265 if self.floatify: target = target.float()
266 input = input.view(-1,input.shape[-1]) if self.is_2d else input.view(-1)
--> 267 return self.func.__call__(input, target.view(-1), *kwargs)
268
269 def CrossEntropyFlat(args, axis:int=-1, *kwargs):

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, input, *kwargs)
491 result = self._slow_forward(input, *kwargs)
492 else:
--> 493 result = self.forward(input, *kwargs)
494 for hook in self._forward_hooks.values():
495 hook_result = hook(self, input, result)

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py in forward(self, input, target)
940 def forward(self, input, target):
941 return F.cross_entropy(input, target, weight=self.weight,
--> 942 ignore_index=self.ignore_index, reduction=self.reduction)
943
944

/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
2054 if size_average is not None or reduce is not None:
2055 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2056 return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
2057
2058

/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
1867 if input.size(0) != target.size(0):
1868 raise ValueError('Expected input batch_size ({}) to match target batch_size ({}).'
-> 1869 .format(input.size(0), target.size(0)))
1870 if dim == 2:
1871 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)

ValueError: Expected input batch_size (8) to match target batch_size (1382400).`

(P.s. I'm relatively inexperienced with fastai and ML in general)

[aviogit]

@WarrenPretorius (and everybody else with this error), I was having the same problem as you, then I realized that writing learn = cnn_learner(...) instead of learn = unet_learner(...) had something to do with this error… :facepalm:

Now I have a more manageable RuntimeError: CUDA error: device-side assert triggered, the buik is done.