xiaohei66 commited on
Commit
7d44592
·
verified ·
1 Parent(s): 02ea008

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md CHANGED
@@ -1,3 +1,66 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ library_name: PaddleOCR
4
+ language:
5
+ - en
6
+ - zh
7
+ pipeline_tag: image-to-text
8
+ tags:
9
+ - OCR
10
+ - PaddlePaddle
11
+ - PaddleOCR
12
+ - wired_table_classification
13
  ---
14
+
15
+ # PP-LCNet_x1_0_table_cls
16
+
17
+ ## Introduction
18
+
19
+ The Table Classification Module is a key component in computer vision systems, responsible for classifying input table images. The performance of this module directly affects the accuracy and efficiency of the entire table recognition process. The Table Classification Module typically receives table images as input and, using deep learning algorithms, classifies them into predefined categories based on the characteristics and content of the images, such as wired and wireless tables. The classification results from the Table Classification Module serve as output for use in table recognition pipelines. The key metrics are as follow:
20
+
21
+ <table>
22
+ <tr>
23
+ <th>Model</th>
24
+ <th>Top1 Acc(%)</th>
25
+ <th>GPU Inference Time (ms)<br/>[Regular Mode / High-Performance Mode]</th>
26
+ <th>CPU Inference Time (ms)<br/>[Regular Mode / High-Performance Mode]</th>
27
+ <th>Model Storage Size (M)</th>
28
+ </tr>
29
+ <tr>
30
+ <td>PP-LCNet_x1_0_table_cls</td>
31
+ <td>94.2</td>
32
+ <td>2.35 / 0.47</td>
33
+ <td>4.03 / 1.35</td>
34
+ <td>6.6M</td>
35
+ </tr>
36
+ </table>
37
+
38
+ ## Model Usage
39
+
40
+ ### Install Dependencies
41
+
42
+ ```shell
43
+ pip install -U paddleocr
44
+ pip install -U onnxruntime-gpu
45
+ ```
46
+
47
+ ### CLI Usage
48
+
49
+ ```shell
50
+ paddleocr table_classification -i ./demo.jpg --model_name PP-LCNet_x1_0_table_cls --engine onnxruntime
51
+ ```
52
+
53
+ ### Python API Usage
54
+
55
+ ```python
56
+ from paddleocr import TableClassification
57
+
58
+ model = TableClassification(
59
+ model_name="PP-LCNet_x1_0_table_cls",
60
+ engine="onnxruntime",
61
+ )
62
+ output = model.predict("./demo.jpg", batch_size=1)
63
+ for res in output:
64
+ res.print()
65
+ res.save_to_json(save_path="./output/res.json")
66
+ ```