qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2026-07-26 05:29:16 +02:00
Code Issues Projects Releases Wiki Activity

training: fix typos found by ruff

Browse source
This commit is contained in:
Robert Sachunsky 2026-07-15 12:46:33 +02:00
parent 0ab6e19f33
commit 4d97e3bf7f
1 changed files with 12 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/eynollah/training/utils.py
View file

@ -1127,13 +1127,21 @@ def preprocess_img_ocr(
if task == 'cnn-rnn-ocr': if task == 'cnn-rnn-ocr':
assert char_to_num, 'task is cnn-rnn-ocr, so preprocess_imgs_ocr should be passed "char_to_num"' assert char_to_num, 'task is cnn-rnn-ocr, so preprocess_imgs_ocr should be passed "char_to_num"'
lab = char_to_num(tf.strings.unicode_split(lab, input_encoding="UTF-8")) lab = char_to_num(tf.strings.unicode_split(lab, input_encoding="UTF-8"))
yield_encoder = lambda x: x def yield_encoder(x):
return x
elif task == 'transformer-ocr': elif task == 'transformer-ocr':
import torch
assert processor, 'task is transformer-ocr, so preprocess_imgs_ocr should be passed "processor"' assert processor, 'task is transformer-ocr, so preprocess_imgs_ocr should be passed "processor"'
# TODO make max_length configurable again, if deemed sensible # TODO make max_length configurable again, if deemed sensible
lab = [l if l != self.processor.tokenizer.pad_token_id else -100 lab = [tok if tok != processor.tokenizer.pad_token_id else -100
for l in processor.tokenizer(lab, padding="max_length", max_length=128).input_ids] for tok in processor.tokenizer(lab,
yield_encoder = lambda img_, lab_: {"pixel_values": processor(Image.fromarray(img_), return_tensors="pt").pixel_values.squeeze(), "labels": torch.tensor(lab_)} padding="max_length",
max_length=128
).input_ids]
def yield_encoder(img_, lab_):
return {"pixel_values": processor(Image.fromarray(img_),
return_tensors="pt").pixel_values.squeeze(),
"labels": torch.tensor(lab_)}
yield yield_encoder(scale_image(img), lab) yield yield_encoder(scale_image(img), lab)
#to_yield = {"image": ret_x, "label": ret_y} #to_yield = {"image": ret_x, "label": ret_y}