Different transform parameters throws error in regression problem

Not sure if this is the right place to post this question, but it would be very nice if somebody has seen this before or knows a way to solve this.

The main issue is for two (example) different transformations
OK => tfms = get_transforms(do_flip=False, p_affine=0, p_lighting=0.75)
NOK => tfms = get_transforms(do_flip=False, max_rotate=25, p_affine=1, p_lighting=0.75)

I first found the error after trying to run “learn.lr_find()”
I tried all kind of things, but after debugging I am think that the enumeration of data.train_dl throws these errors

for x in enumerate(data.train_dl):

But after some real look into the fastai library, pytorch and even the c-code that eventually give the error I was not able to find out why and where this goes wrong. As said very nice if somebody knows a solution

More details of what I am doing:
The issue is in a similar model as the headpose example showed in lesson 3, where the middle of the face is detected. I use my pictures of meters and I like to recognize the topcorner of a label with the identifying number. Because the testset is rather small I like to use a lot of augmentation.

After the following error messages I pasted two screenshots of one OK, another not OK

#OK tfms = get_transforms(do_flip=False, p_affine=0, p_lighting=0.75)
#Beneath is the tfms giving errors
tfms = get_transforms(do_flip=False, max_rotate=25, p_affine=1, p_lighting=0.75)

data = (ImageItemList.from_folder(path)
        .label_from_func(get_ctr, label_cls=PointsItemList)
        .transform(tfms, tfm_y=True, padding_mode='border')

learn = create_cnn(data, models.resnet34)


Fulll error message

RuntimeError                              Traceback (most recent call last)
<ipython-input-20-5aa600e31cfe> in <module>()
----> 1 learn.lr_find()
      2 learn.recorder.plot()

~/anaconda3/lib/python3.6/site-packages/fastai/train.py in lr_find(learn, start_lr, end_lr, num_it, stop_div, **kwargs)
     26     cb = LRFinder(learn, start_lr, end_lr, num_it, stop_div)
     27     a = int(np.ceil(num_it/len(learn.data.train_dl)))
---> 28     learn.fit(a, start_lr, callbacks=[cb], **kwargs)
     30 def to_fp16(learn:Learner, loss_scale:float=512., flat_master:bool=False)->Learner:

~/anaconda3/lib/python3.6/site-packages/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks)
    160         callbacks = [cb(self) for cb in self.callback_fns] + listify(callbacks)
    161         fit(epochs, self.model, self.loss_func, opt=self.opt, data=self.data, metrics=self.metrics,
--> 162             callbacks=self.callbacks+callbacks)
    164     def create_opt(self, lr:Floats, wd:Floats=0.)->None:

~/anaconda3/lib/python3.6/site-packages/fastai/basic_train.py in fit(epochs, model, loss_func, opt, data, callbacks, metrics)
     92     except Exception as e:
     93         exception = e
---> 94         raise e
     95     finally: cb_handler.on_train_end(exception)

~/anaconda3/lib/python3.6/site-packages/fastai/basic_train.py in fit(epochs, model, loss_func, opt, data, callbacks, metrics)
     80             cb_handler.on_epoch_begin()
---> 82             for xb,yb in progress_bar(data.train_dl, parent=pbar):
     83                 xb, yb = cb_handler.on_batch_begin(xb, yb)
     84                 loss = loss_batch(model, xb, yb, loss_func, opt, cb_handler)

~/anaconda3/lib/python3.6/site-packages/fastprogress/fastprogress.py in __iter__(self)
     63         self.update(0)
     64         try:
---> 65             for i,o in enumerate(self._gen):
     66                 yield o
     67                 if self.auto_update: self.update(i+1)

~/anaconda3/lib/python3.6/site-packages/fastai/basic_data.py in __iter__(self)
     45     def __iter__(self):
     46         "Process and returns items from `DataLoader`."
---> 47         for b in self.dl:
     48             y = b[1][0] if is_listy(b[1]) else b[1]
     49             if not self.skip_size1 or y.size(0) != 1: yield self.proc_batch(b)

~/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py in __next__(self)
    635                 self.reorder_dict[idx] = batch
    636                 continue
--> 637             return self._process_next_batch(batch)
    639     next = __next__  # Python 2 compatibility

~/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py in _process_next_batch(self, batch)
    656         self._put_indices()
    657         if isinstance(batch, ExceptionWrapper):
--> 658             raise batch.exc_type(batch.exc_msg)
    659         return batch

RuntimeError: Traceback (most recent call last):
  File "/home/paperspace/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/home/paperspace/anaconda3/lib/python3.6/site-packages/fastai/torch_core.py", line 94, in data_collate
    return torch.utils.data.dataloader.default_collate(to_data(batch))
  File "/home/paperspace/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 232, in default_collate
    return [default_collate(samples) for samples in transposed]
  File "/home/paperspace/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 232, in <listcomp>
    return [default_collate(samples) for samples in transposed]
  File "/home/paperspace/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 209, in default_collate
    return torch.stack(batch, 0, out=out)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 1 and 0 in dimension 1 at /opt/conda/conda-bld/pytorch-nightly_1542272393570/work/aten/src/TH/generic/THTensorMoreMath.cpp:1319