lpbeaulieu / typewriter-ocr-tintypetext Goto Github PK

First - awesome project and I am fascinated by the idea of an OCR trained to my own typewriter. However, I cannot run the training successfully. Here is what I get:

(ocr) fred@banane:~/Documents/ML/Typewriter-OCR-TintypeText$ python3 train_model.py
/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/callback/core.py:69: UserWarning: You are shadowing an attribute (modules) that exists in the learner. Use self.learn.modules to avoid this
warn(f"You are shadowing an attribute ({name}) that exists in the learner. Use self.learn.{name} to avoid this")
epoch train_loss valid_loss accuracy time
Traceback (most recent call last):-------------------------------------------------------------------------------| 0.00% [0/1 00:00<?]
File "/home/fred/Documents/ML/Typewriter-OCR-TintypeText/train_model.py", line 60, in
learn = fit()
^^^^^
File "/home/fred/Documents/ML/Typewriter-OCR-TintypeText/train_model.py", line 49, in fit
learn.fit_one_cycle(epochs, learning_rate)
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/callback/schedule.py", line 119, in fit_one_cycle
self.fit(n_epoch, cbs=ParamScheduler(scheds)+L(cbs), reset_opt=reset_opt, wd=wd, start_epoch=start_epoch)
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 264, in fit
self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 199, in with_events
try: self(f'before{event_type}'); f()
^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 253, in _do_fit
self._with_events(self._do_epoch, 'epoch', CancelEpochException)
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 199, in with_events
try: self(f'before{event_type}'); f()
^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 248, in _do_epoch
self._do_epoch_validate()
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 244, in _do_epoch_validate
with torch.no_grad(): self._with_events(self.all_batches, 'validate', CancelValidException)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 199, in with_events
try: self(f'before{event_type}'); f()
^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/learner.py", line 205, in all_batches
for o in enumerate(self.dl): self.one_batch(*o)
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/load.py", line 127, in iter
for b in _loadersself.fake_l.num_workers==0:
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 631, in next
data = self._next_data()
^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 1346, in _next_data
return self._process_data(data)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 1372, in _process_data
data.reraise()
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/torch/_utils.py", line 722, in reraise
raise exception
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/transforms.py", line 261, in encodes
return TensorCategory(self.vocab.o2i[o])
~~~~~~~~~~~~~~^^^
KeyError: 'S'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 41, in fetch
data = next(self.dataset_iter)
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/load.py", line 138, in create_batches
yield from map(self.do_batch, self.chunkify(res))
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastcore/basics.py", line 230, in chunked
res = list(itertools.islice(it, chunk_sz))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/load.py", line 168, in do_item
try: return self.after_item(self.create_item(s))
^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/load.py", line 175, in create_item
if self.indexed: return self.dataset[s or 0]
~~~~~~~~~~~~^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/core.py", line 447, in getitem
res = tuple([tl[it] for tl in self.tls])
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/core.py", line 447, in
res = tuple([tl[it] for tl in self.tls])
~~^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/core.py", line 406, in getitem
return self._after_item(res) if is_indexer(idx) else res.map(self._after_item)
^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/core.py", line 366, in _after_item
def _after_item(self, o): return self.tfms(o)
^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastcore/transform.py", line 208, in call
def call(self, o): return compose_tfms(o, tfms=self.fs, split_idx=self.split_idx)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastcore/transform.py", line 158, in compose_tfms
x = f(x, **kwargs)
^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastcore/transform.py", line 81, in call
def call(self, x, **kwargs): return self._call('encodes', x, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastcore/transform.py", line 91, in _call
return self._do_call(getattr(self, fn), x, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastcore/transform.py", line 97, in _do_call
return retain_type(f(x, **kwargs), x, ret)
^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastcore/dispatch.py", line 120, in call
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/home/fred/anaconda3/envs/ocr/lib/python3.11/site-packages/fastai/data/transforms.py", line 263, in encodes
raise KeyError(f"Label '{o}' was not included in the training dataset") from e
KeyError: "Label 'S' was not included in the training dataset"

I do have a folder "Dataset" and I do have a subfolder "S" with a file called "S-38.jpg" sized 106 x 164 pics. What can I do? Thank you.