Skip to content

Latest commit

 

History

History
98 lines (69 loc) · 8.49 KB

figures_en.md

File metadata and controls

98 lines (69 loc) · 8.49 KB
Raw

Detailed Features

1. Various Pre-training Models

1.1. Image

Examples of Boutique Models
Image Classification Dish Identification, Animal Identification, Animal Identification, -->More
Object Detection Universal Detection, Pedestrian Detection, Vehicle Detection, -->More
Face Detection Face Detection, Mask Detection, -->More
Image Segmentation Portrait Segmentation, Body Analysis, Pneumonia CT Imaging Analysis, -->More
Key Point Detection Body Key Points, Face Key Points, Hands Key Points, -->More
Text Recognition Ultra Lightweight Chinese & English OCR Text Recognition, -->More
Image Generation Style Migration, Street View Cartoon, -->More
Image Editing Super Resolution, B&W Color, -->More

1.2 Text

Examples of Boutique Models
Word Analysis Linguistic Analysis, Syntactic Analysis, -->More
Sentiment Analysis Emotion Judgment, Emotion Analysis, -->More
Text Review Porn Review, -->More
Text Generation Poetic Couplet Generation, Love Letters Generation, Popular Love Letters, -->More
Semantic Models ERNIE, Text Similarity, -->More

1.3. Speech

Examples of Boutique Models
Text-to-speech Text-to-speech, -->More

1.4. Video

Examples of Boutique Models
Video Classification Video Classification, -->More

2. One-key Model Prediction

  • For example, if you use the lightweight Chinese OCR model chinese_ocr_db_crnn_mobile for text recognition, you can quickly recognize the text in an image with pressing one key.
$ pip install paddlehub
$ wget https://paddlehub.bj.bcebos.com/model/image/ocr/test_ocr.jpg
$ hub run chinese_ocr_db_crnn_mobile --input_path test_ocr.jpg --visualization=True
  • The prediction results images are stored in the ocr_result folder under the current path, as shown in the following figure.

* Use the lexical analysis model LAC for word segmentation. 

$ hub run lac --input_text "现在，慕尼黑再保险公司不仅是此类行动的倡议者，更是将其大量气候数据整合进保险产品中，并与公众共享大量天气信息，参与到新能源领域的保障中。"
[{
    'word': ['现在', '，', '慕尼黑再保险公司', '不仅', '是', '此类', '行动', '的', '倡议者', '，', '更是', '将', '其', '大量', '气候', '数据', '整合', '进', '保险', '产品', '中', '，', '并', '与', '公众', '共享', '大量', '天气', '信息', '，', '参与', '到', '新能源', '领域', '的', '保障', '中', '。'],
    'tag':  ['TIME', 'w', 'ORG', 'c', 'v', 'r', 'n', 'u', 'n', 'w', 'd', 'p', 'r', 'a', 'n', 'n', 'v', 'v', 'n', 'n', 'f', 'w', 'c', 'p', 'n', 'v', 'a', 'n', 'n', 'w', 'v', 'v', 'n', 'n', 'u', 'vn', 'f', 'w']
}]

In addition to one-line code prediction, PaddleHub also supports the use of API to revoke the model. For details, refer to the detailed documentation of each model.

3. One-Key to deploy Models as Services

PaddleHub provides convenient model-to-service capability to deploy HTTP services for models with one simple command. The LAC lexical analysis service can quickly start with the following commands:

$ hub serving start -m chinese_ocr_db_crnn_mobile

For more instructions on using Model Serving, See PaddleHub Model One-Key Model Serving Deployment.

4. Transfer Learning within Ten Lines of Codes

With the Fine-tune API, deep learning models can be migrated and learned in computer vision scenarios with a small number of codes.

Transfer Learning within Ten Lines of Codes

  • For a quick online experience, click PaddleHub Tutorial Collection to use the GPU computing power provided by AI Studio platform for a quick attempt.