فهرست منبع

updata cls docs (#2958)

zhangyubo0722 10 ماه پیش
والد
کامیت
ac38cb3a61

+ 2 - 2
docs/module_usage/tutorials/cv_modules/image_classification.md

@@ -691,8 +691,8 @@ for res in output:
 ```
 
 运行后,得到的结果为:
-```josn
-{'res': {'input_path': 'test_imgs/general_image_classification_001.jpg', 'class_ids': [296, 279, 270, 537, 356], 'scores': [0.7915499806404114, 0.0173799991607666, 0.014279999770224094, 0.013009999878704548, 0.01221999991685152], 'label_names': ['ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus', 'Arctic fox, white fox, Alopex lagopus', 'white wolf, Arctic wolf, Canis lupus tundrarum', 'dogsled, dog sled, dog sleigh', 'weasel']}}
+```bash
+{'res': {'input_path': 'general_image_classification_001.jpg', 'page_index': None, 'class_ids': array([296, 279, 270, 537, 356], dtype=int32), 'scores': array([0.79155, 0.01738, 0.01428, 0.01301, 0.01222], dtype=float32), 'label_names': ['ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus', 'Arctic fox, white fox, Alopex lagopus', 'white wolf, Arctic wolf, Canis lupus tundrarum', 'dogsled, dog sled, dog sleigh', 'weasel']}}
 ```
 
 运行结果参数含义如下:

+ 2 - 2
docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md

@@ -51,8 +51,8 @@ for res in output:
 ```
 
 运行后,得到的结果为:
-```josn
-{'res': {'input_path': 'test_imgs/img_rot180_demo.jpg', 'class_ids': [2], 'scores': [0.8816400170326233], 'label_names': ['180']}}
+```bash
+{'res': {'input_path': 'test_imgs/img_rot180_demo.jpg', 'page_index': None, 'class_ids': array([2], dtype=int32), 'scores': array([0.88164], dtype=float32), 'label_names': ['180']}}
 ```
 
 运行结果参数含义如下:

+ 9 - 9
docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.md

@@ -52,8 +52,8 @@ for res in output:
 ```
 
 运行后,得到的结果为:
-```josn
-{'res': {'input_path': 'test_imgs/textline_rot180_demo.jpg', 'class_ids': [1], 'scores': [1.0], 'label_names': ['180_degree']}}
+```bash
+{'res': {'input_path': 'textline_rot180_demo.jpg', 'page_index': None, 'class_ids': array([1], dtype=int32), 'scores': array([1.], dtype=float32), 'label_names': ['180_degree']}}
 ```
 
 运行结果参数含义如下:
@@ -251,7 +251,7 @@ python main.py -c paddlex/configs/modules/textline_orientation/PP-LCNet_x0_25_te
   "attributes": {
     "label_file": "..\/..\/dataset\/textline_orientation_example_data\/label.txt",
     "num_classes": 2,
-    "train_samples": 1000,
+    "train_samples": 1760,
     "train_sample_paths": [
       "check_dataset\/demo_img\/ILSVRC2012_val_00019234_4284.jpg",
       "check_dataset\/demo_img\/lsvt_train_images_4655.jpg",
@@ -264,7 +264,7 @@ python main.py -c paddlex/configs/modules/textline_orientation/PP-LCNet_x0_25_te
       "check_dataset\/demo_img\/25959328_518853598.jpg",
       "check_dataset\/demo_img\/ILSVRC2012_val_00018420_14077.jpg"
     ],
-    "val_samples": 200,
+    "val_samples": 440,
     "val_sample_paths": [
       "check_dataset\/demo_img\/lsvt_train_images_79109.jpg",
       "check_dataset\/demo_img\/lsvt_train_images_131133.jpg",
@@ -281,16 +281,16 @@ python main.py -c paddlex/configs/modules/textline_orientation/PP-LCNet_x0_25_te
   "analysis": {
     "histogram": "check_dataset\/histogram.png"
   },
-  "dataset_path": ".\/dataset\/textline_orientation_example_data",
+  "dataset_path": "textline_orientation_example_data",
   "show_type": "image",
   "dataset_type": "ClsDataset"
 }
 </code></pre>
 <p>上述校验结果中,check_pass 为 True 表示数据集格式符合要求,其他部分指标的说明如下:</p>
 <ul>
-<li><code>attributes.num_classes</code>:该数据集类别数为 4;</li>
-<li><code>attributes.train_samples</code>:该数据集训练集样本数量为 1552;</li>
-<li><code>attributes.val_samples</code>:该数据集验证集样本数量为 2593;</li>
+<li><code>attributes.num_classes</code>:该数据集类别数为 2;</li>
+<li><code>attributes.train_samples</code>:该数据集训练集样本数量为 1760;</li>
+<li><code>attributes.val_samples</code>:该数据集验证集样本数量为 440;</li>
 <li><code>attributes.train_sample_paths</code>:该数据集训练集样本可视化图片相对路径列表;</li>
 <li><code>attributes.val_sample_paths</code>:该数据集验证集样本可视化图片相对路径列表;</li>
 </ul>
@@ -414,7 +414,7 @@ python main.py -c paddlex/configs/modules/textline_orientation/PP-LCNet_x0_25_te
 
 1.<b>产线集成</b>
 
-文本行方向分类模块可以集成的PaddleX产线有[文档场景信息抽取v3产线(PP-ChatOCRv3)](../../../pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction.md),只需要替换模型路径即可完成文本行方向分类模块的模型更新。
+文本行方向分类模块可以集成的PaddleX产线有[通用OCR产线](../../../pipeline_usage/tutorials/ocr_pipelines/OCR.md)和[文档场景信息抽取v3产线(PP-ChatOCRv3)](../../../pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction.md),只需要替换模型路径即可完成文本行方向分类模块的模型更新。
 
 2.<b>模块集成</b>