cnocr 2.3__tar.gz → 2.3.0.2__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (61) hide show
  1. {cnocr-2.3 → cnocr-2.3.0.2}/PKG-INFO +16 -5
  2. {cnocr-2.3 → cnocr-2.3.0.2}/README.md +15 -4
  3. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/__version__.py +1 -1
  4. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/cli.py +16 -6
  5. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/consts.py +1 -1
  6. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/utility.py +1 -1
  7. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr.egg-info/PKG-INFO +16 -5
  8. {cnocr-2.3 → cnocr-2.3.0.2}/LICENSE +0 -0
  9. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/__init__.py +0 -0
  10. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/app.py +0 -0
  11. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/classification/__init__.py +0 -0
  12. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/classification/dataset.py +0 -0
  13. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/classification/image_classifier.py +0 -0
  14. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/clf_cli.py +0 -0
  15. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/cn_ocr.py +0 -0
  16. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/data_utils/__init__.py +0 -0
  17. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/data_utils/aug.py +0 -0
  18. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/data_utils/block_shuffle.py +0 -0
  19. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/data_utils/transforms.py +0 -0
  20. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/data_utils/utils.py +0 -0
  21. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/dataset.py +0 -0
  22. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/dataset_utils.py +0 -0
  23. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/gradio_app.py +0 -0
  24. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/gradio_app2.py +0 -0
  25. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/label_cn.txt +0 -0
  26. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/label_number.txt +0 -0
  27. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/line_split.py +0 -0
  28. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/lr_scheduler.py +0 -0
  29. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/models/__init__.py +0 -0
  30. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/models/ctc.py +0 -0
  31. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/models/densenet.py +0 -0
  32. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/models/mobilenet.py +0 -0
  33. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/models/ocr_model.py +0 -0
  34. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/__init__.py +0 -0
  35. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/consts.py +0 -0
  36. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/postprocess/__init__.py +0 -0
  37. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/postprocess/rec_postprocess.py +0 -0
  38. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/pp_recognizer.py +0 -0
  39. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/utils/__init__.py +0 -0
  40. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/utils/chinese_cht_dict.txt +0 -0
  41. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/utils/en_dict.txt +0 -0
  42. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/ppocr/utils/ppocr_keys_v1.txt +0 -0
  43. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/recognizer.py +0 -0
  44. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/serve.py +0 -0
  45. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/trainer.py +0 -0
  46. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr/utils.py +0 -0
  47. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr.egg-info/SOURCES.txt +0 -0
  48. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr.egg-info/dependency_links.txt +0 -0
  49. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr.egg-info/entry_points.txt +0 -0
  50. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr.egg-info/not-zip-safe +0 -0
  51. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr.egg-info/requires.txt +0 -0
  52. {cnocr-2.3 → cnocr-2.3.0.2}/cnocr.egg-info/top_level.txt +0 -0
  53. {cnocr-2.3 → cnocr-2.3.0.2}/setup.cfg +0 -0
  54. {cnocr-2.3 → cnocr-2.3.0.2}/setup.py +0 -0
  55. {cnocr-2.3 → cnocr-2.3.0.2}/tests/test_cnocr.py +0 -0
  56. {cnocr-2.3 → cnocr-2.3.0.2}/tests/test_dataset.py +0 -0
  57. {cnocr-2.3 → cnocr-2.3.0.2}/tests/test_models.py +0 -0
  58. {cnocr-2.3 → cnocr-2.3.0.2}/tests/test_ppocr.py +0 -0
  59. {cnocr-2.3 → cnocr-2.3.0.2}/tests/test_pytorch.py +0 -0
  60. {cnocr-2.3 → cnocr-2.3.0.2}/tests/test_trainer.py +0 -0
  61. {cnocr-2.3 → cnocr-2.3.0.2}/tests/test_transforms.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: cnocr
3
- Version: 2.3
3
+ Version: 2.3.0.2
4
4
  Summary: Python3 package for Chinese/English OCR, with small pretrained models
5
5
  Home-page: https://github.com/breezedeus/cnocr
6
6
  Author: breezedeus
@@ -32,6 +32,7 @@ License-File: LICENSE
32
32
  <img src="./docs/figs/cnocr-logo.jpg" width="250px"/>
33
33
  <div>&nbsp;</div>
34
34
 
35
+ [![Discord](https://img.shields.io/discord/1200765964434821260?label=Discord)](https://discord.gg/GgD87WM8Tf)
35
36
  [![Downloads](https://static.pepy.tech/personalized-badge/cnocr?period=total&units=international_system&left_color=grey&right_color=orange&left_text=Downloads)](https://pepy.tech/project/cnocr)
36
37
  [![Visitors](https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2Fbreezedeus%2FCnOCR&label=Visitors&countColor=%23f5c791&style=flat&labelStyle=none)](https://visitorbadge.io/status?path=https%3A%2F%2Fgithub.com%2Fbreezedeus%2FCnOCR)
37
38
  [![license](https://img.shields.io/github/license/breezedeus/cnocr)](./LICENSE)
@@ -322,6 +323,16 @@ $ pip install cnocr[ort-cpu] -i https://mirrors.aliyun.com/pypi/simple
322
323
 
323
324
 
324
325
 
326
+ ### Docker Image
327
+
328
+ 可以从 [Docker Hub](https://hub.docker.com/u/breezedeus) 直接拉取已安装好 CnOCR 的镜像使用。
329
+
330
+ ```bash
331
+ $ docker pull breezedeus/cnocr:latest
332
+ ```
333
+
334
+ 更多说明可见 [安装文档](https://cnocr.readthedocs.io/zh/latest/install/)。
335
+
325
336
 
326
337
 
327
338
  ## HTTP服务
@@ -429,14 +440,14 @@ print(ocr_out)
429
440
  | **densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
430
441
  | **scene-densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
431
442
  | **doc-densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
432
- | **densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
433
- | **scene-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
434
- | **doc-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
443
+ | **densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
444
+ | **scene-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
445
+ | **doc-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
435
446
  | **densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104812055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
436
447
  | **scene-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104815055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
437
448
  | **doc-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104820055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
438
449
  | **number-densenet_lite_136-fc** 🆕 | √ | √ | cnocr | 2.7 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
439
- | **number-densenet_lite_136-gru** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 5.5 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
450
+ | **number-densenet_lite_136-gru** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 5.5 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
440
451
  | **number-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104055055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 55 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
441
452
  | ch_PP-OCRv3 | X | √ | ppocr | 10 M | 简体中文、英文、数字 | √ |
442
453
  | ch_ppocr_mobile_v2.0 | X | √ | ppocr | 4.2 M | 简体中文、英文、数字 | √ |
@@ -2,6 +2,7 @@
2
2
  <img src="./docs/figs/cnocr-logo.jpg" width="250px"/>
3
3
  <div>&nbsp;</div>
4
4
 
5
+ [![Discord](https://img.shields.io/discord/1200765964434821260?label=Discord)](https://discord.gg/GgD87WM8Tf)
5
6
  [![Downloads](https://static.pepy.tech/personalized-badge/cnocr?period=total&units=international_system&left_color=grey&right_color=orange&left_text=Downloads)](https://pepy.tech/project/cnocr)
6
7
  [![Visitors](https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2Fbreezedeus%2FCnOCR&label=Visitors&countColor=%23f5c791&style=flat&labelStyle=none)](https://visitorbadge.io/status?path=https%3A%2F%2Fgithub.com%2Fbreezedeus%2FCnOCR)
7
8
  [![license](https://img.shields.io/github/license/breezedeus/cnocr)](./LICENSE)
@@ -292,6 +293,16 @@ $ pip install cnocr[ort-cpu] -i https://mirrors.aliyun.com/pypi/simple
292
293
 
293
294
 
294
295
 
296
+ ### Docker Image
297
+
298
+ 可以从 [Docker Hub](https://hub.docker.com/u/breezedeus) 直接拉取已安装好 CnOCR 的镜像使用。
299
+
300
+ ```bash
301
+ $ docker pull breezedeus/cnocr:latest
302
+ ```
303
+
304
+ 更多说明可见 [安装文档](https://cnocr.readthedocs.io/zh/latest/install/)。
305
+
295
306
 
296
307
 
297
308
  ## HTTP服务
@@ -399,14 +410,14 @@ print(ocr_out)
399
410
  | **densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
400
411
  | **scene-densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
401
412
  | **doc-densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
402
- | **densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
403
- | **scene-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
404
- | **doc-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
413
+ | **densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
414
+ | **scene-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
415
+ | **doc-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
405
416
  | **densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104812055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
406
417
  | **scene-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104815055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
407
418
  | **doc-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104820055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
408
419
  | **number-densenet_lite_136-fc** 🆕 | √ | √ | cnocr | 2.7 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
409
- | **number-densenet_lite_136-gru** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 5.5 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
420
+ | **number-densenet_lite_136-gru** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 5.5 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
410
421
  | **number-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104055055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 55 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
411
422
  | ch_PP-OCRv3 | X | √ | ppocr | 10 M | 简体中文、英文、数字 | √ |
412
423
  | ch_ppocr_mobile_v2.0 | X | √ | ppocr | 4.2 M | 简体中文、英文、数字 | √ |
@@ -17,4 +17,4 @@
17
17
  # specific language governing permissions and limitations
18
18
  # under the License.
19
19
 
20
- __version__ = '2.3'
20
+ __version__ = '2.3.0.2'
@@ -224,6 +224,9 @@ def visualize_example(example, fp_prefix):
224
224
  default='onnx',
225
225
  help='检测模型类型。默认值为 `onnx`',
226
226
  )
227
+ @click.option(
228
+ '--det-resized-shape', type=int, default=768, help='检测模型输入图像尺寸。默认值为 768',
229
+ )
227
230
  @click.option(
228
231
  '-p',
229
232
  '--pretrained-model-fp',
@@ -251,6 +254,9 @@ def visualize_example(example, fp_prefix):
251
254
  @click.option(
252
255
  "--draw-font-path", default='./docs/fonts/simfang.ttf', help="画出检测与识别效果图时使用的字体文件",
253
256
  )
257
+ @click.option(
258
+ "--show-details", is_flag=True, default=False, help="是否打印识别结果详情。默认值为 `False`",
259
+ )
254
260
  @click.option(
255
261
  "--verbose", is_flag=True, default=False, help="是否打印详细日志信息。默认值为 `False`",
256
262
  )
@@ -260,12 +266,14 @@ def predict(
260
266
  rec_vocab_fp,
261
267
  det_model_name,
262
268
  det_model_backend,
269
+ det_resized_shape,
263
270
  pretrained_model_fp,
264
271
  context,
265
272
  img_file_or_dir,
266
273
  single_line,
267
274
  draw_results_dir,
268
275
  draw_font_path,
276
+ show_details,
269
277
  verbose,
270
278
  ):
271
279
  """模型预测""",
@@ -298,18 +306,24 @@ def predict(
298
306
  # det_more_configs={'rotated_bbox': False},
299
307
  )
300
308
  ocr_func = ocr.ocr_for_single_line if single_line else ocr.ocr
309
+ ocr_kwargs = {}
310
+ if not single_line:
311
+ ocr_kwargs['resized_shape'] = det_resized_shape
301
312
 
302
313
  for fp in fp_list:
303
314
  start_time = time.time()
304
315
  logger.info('\n' + '=' * 10 + fp + '=' * 10)
305
316
  res = ocr_func(
306
317
  fp,
307
- # resized_shape=2280,
318
+ **ocr_kwargs,
308
319
  # box_score_thresh=0.14,
309
320
  # min_box_size=20,
310
321
  )
311
322
  logger.info('time cost: %f' % (time.time() - start_time))
312
- logger.info(res)
323
+ if show_details:
324
+ logger.info(res)
325
+ else:
326
+ logger.info('\n'.join([line_res['text'] for line_res in res]))
313
327
  if single_line:
314
328
  res = [res]
315
329
 
@@ -329,10 +343,6 @@ def predict(
329
343
  fp, res, out_draw_fp=out_draw_fp, font_path=draw_font_path
330
344
  )
331
345
 
332
- # for line_res in res:
333
- # preds, prob = line_res['text'], line_res['score']
334
- # logger.info('\npred: %s, with score %f' % (''.join(preds), prob))
335
-
336
346
 
337
347
  @cli.command('evaluate')
338
348
  @click.option(
@@ -33,7 +33,7 @@ logger = logging.getLogger(__name__)
33
33
  # 模型版本只对应到第二层,第三层的改动表示模型兼容。
34
34
  # 如: __version__ = '2.2.*',对应的 MODEL_VERSION 都是 '2.2'
35
35
  MODEL_VERSION = '.'.join(__version__.split('.', maxsplit=2)[:2])
36
- DOWNLOAD_SOURCE = os.environ.get('CNOCR_DOWNLOAD_SOURCE', 'CN')
36
+ DOWNLOAD_SOURCE = os.environ.get('CNOCR_DOWNLOAD_SOURCE', 'HF')
37
37
 
38
38
  IMG_STANDARD_HEIGHT = 32
39
39
  CN_VOCAB_FP = Path(__file__).parent.absolute() / 'label_cn.txt'
@@ -167,7 +167,7 @@ def create_predictor(model_dir, mode, ort_providers=None):
167
167
  if not os.path.exists(model_file_path):
168
168
  raise ValueError("not find model file path {}".format(
169
169
  model_file_path))
170
- if ort_providers is not None:
170
+ if ort_providers is None:
171
171
  ort_providers = get_default_ort_providers()
172
172
  logger.debug(f'ort providers: {ort_providers}')
173
173
  sess = ort.InferenceSession(model_file_path, providers=ort_providers)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: cnocr
3
- Version: 2.3
3
+ Version: 2.3.0.2
4
4
  Summary: Python3 package for Chinese/English OCR, with small pretrained models
5
5
  Home-page: https://github.com/breezedeus/cnocr
6
6
  Author: breezedeus
@@ -32,6 +32,7 @@ License-File: LICENSE
32
32
  <img src="./docs/figs/cnocr-logo.jpg" width="250px"/>
33
33
  <div>&nbsp;</div>
34
34
 
35
+ [![Discord](https://img.shields.io/discord/1200765964434821260?label=Discord)](https://discord.gg/GgD87WM8Tf)
35
36
  [![Downloads](https://static.pepy.tech/personalized-badge/cnocr?period=total&units=international_system&left_color=grey&right_color=orange&left_text=Downloads)](https://pepy.tech/project/cnocr)
36
37
  [![Visitors](https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2Fbreezedeus%2FCnOCR&label=Visitors&countColor=%23f5c791&style=flat&labelStyle=none)](https://visitorbadge.io/status?path=https%3A%2F%2Fgithub.com%2Fbreezedeus%2FCnOCR)
37
38
  [![license](https://img.shields.io/github/license/breezedeus/cnocr)](./LICENSE)
@@ -322,6 +323,16 @@ $ pip install cnocr[ort-cpu] -i https://mirrors.aliyun.com/pypi/simple
322
323
 
323
324
 
324
325
 
326
+ ### Docker Image
327
+
328
+ 可以从 [Docker Hub](https://hub.docker.com/u/breezedeus) 直接拉取已安装好 CnOCR 的镜像使用。
329
+
330
+ ```bash
331
+ $ docker pull breezedeus/cnocr:latest
332
+ ```
333
+
334
+ 更多说明可见 [安装文档](https://cnocr.readthedocs.io/zh/latest/install/)。
335
+
325
336
 
326
337
 
327
338
  ## HTTP服务
@@ -429,14 +440,14 @@ print(ocr_out)
429
440
  | **densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
430
441
  | **scene-densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
431
442
  | **doc-densenet_lite_136-gru** 🆕 | √ | √ | cnocr | 12 M | 简体中文、英文、数字 | X |
432
- | **densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
433
- | **scene-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
434
- | **doc-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
443
+ | **densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
444
+ | **scene-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
445
+ | **doc-densenet_lite_246-gru_base** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 25 M | 简体中文、英文、数字 | X |
435
446
  | **densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104812055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
436
447
  | **scene-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104815055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
437
448
  | **doc-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104820055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 82 M | 简体中文、英文、数字 | X |
438
449
  | **number-densenet_lite_136-fc** 🆕 | √ | √ | cnocr | 2.7 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
439
- | **number-densenet_lite_136-gru** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享,2 月开源) | √ | √ | cnocr | 5.5 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
450
+ | **number-densenet_lite_136-gru** 🆕 <br /> ([星球会员](https://t.zsxq.com/FEYZRJQ)专享) | √ | √ | cnocr | 5.5 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
440
451
  | **number-densenet_lite_666-gru_large** 🆕 <br />(购买链接:[B站](https://gf.bilibili.com/item/detail/1104055055)、[Lemon Squeezy](https://ocr.lemonsqueezy.com/)) | √ | √ | cnocr | 55 M | **纯数字**(仅包含 `0~9` 十个数字) | X |
441
452
  | ch_PP-OCRv3 | X | √ | ppocr | 10 M | 简体中文、英文、数字 | √ |
442
453
  | ch_ppocr_mobile_v2.0 | X | √ | ppocr | 4.2 M | 简体中文、英文、数字 | √ |
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes