mirror of
https://github.com/qurator-spk/eynollah.git
synced 2026-02-20 16:32:03 +01:00
27f43c175f
major conflicts resolved manually:
- branches for non-`light` segmentation already removed in main
- Keras/TF setup and no TF1 sessions, esp. in new ModelZoo
- changes to binarizer and its CLI (`mode`, `overwrite`, `run_single()`)
- writer: `build...` w/ kwargs instead of positional
- training for segmentation/binarization/enhancement tasks:
* drop unused `generate_data_from_folder()`
* simplify `preprocess_imgs()`: turn `preprocess_img()`, `get_patches()`
and `get_patches_num_scale_new()` into generators, only writing
result files in the caller (top-level loop) instead of passing
output directories and file counter
- training for new OCR task:
* `train`: put keys into additional `config_params` where they belong,
resp. (conditioned under existing keys), and w/ better documentation
* `train`: add new keys as kwargs to `run()` to make usable
* `utils`: instead of custom data loader `data_gen_ocr()`, re-use
existing `preprocess_imgs()` (for cfg capture and top-level loop),
but extended w/ new kwargs and calling new `preprocess_img_ocr()`;
the latter as single-image generator (also much simplified)
* `train`: use tf.data loader pipeline from that generator w/ standard
mechanisms for batching, shuffling, prefetching etc.
* `utils` and `train`: instead of `vectorize_label`, use `Dataset.padded_batch`
* add TensorBoard callback and re-use our checkpoint callback
* also use standard Keras top-level loop for training
still problematic (substantially unresolved):
- `Patches` now only w/ fixed implicit size
(ignoring training config params)
- `PatchEncoder` now only w/ fixed implicit num patches and projection dim
(ignoring training config params)
53 lines
1.4 KiB
Python
53 lines
1.4 KiB
Python
import pytest
|
|
from PIL import Image
|
|
|
|
@pytest.mark.parametrize(
|
|
"options",
|
|
[
|
|
[], # defaults
|
|
["--no-patches"],
|
|
], ids=str)
|
|
def test_run_eynollah_binarization_filename(
|
|
tmp_path,
|
|
run_eynollah_ok_and_check_logs,
|
|
resources_dir,
|
|
options,
|
|
):
|
|
infile = resources_dir / '2files/kant_aufklaerung_1784_0020.tif'
|
|
outfile = tmp_path / 'kant_aufklaerung_1784_0020.png'
|
|
run_eynollah_ok_and_check_logs(
|
|
'binarization',
|
|
[
|
|
'-i', str(infile),
|
|
'-o', str(outfile),
|
|
] + options,
|
|
[
|
|
'Loaded model'
|
|
]
|
|
)
|
|
assert outfile.exists()
|
|
with Image.open(infile) as original_img:
|
|
original_size = original_img.size
|
|
with Image.open(outfile) as binarized_img:
|
|
binarized_size = binarized_img.size
|
|
assert original_size == binarized_size
|
|
|
|
def test_run_eynollah_binarization_directory(
|
|
tmp_path,
|
|
run_eynollah_ok_and_check_logs,
|
|
resources_dir,
|
|
image_resources,
|
|
):
|
|
outdir = tmp_path
|
|
run_eynollah_ok_and_check_logs(
|
|
'binarization',
|
|
[
|
|
'-di', str(resources_dir / '2files'),
|
|
'-o', str(outdir),
|
|
],
|
|
[
|
|
f'Binarizing [ 1/2] {image_resources[0].name}',
|
|
f'Binarizing [ 2/2] {image_resources[1].name}',
|
|
]
|
|
)
|
|
assert len(list(outdir.iterdir())) == 2
|