- PaddleHub aims to provide developers with rich, high-quality, and directly usable pre-trained models.
-**No need for deep learning background**, you can use AI models quickly and enjoy the dividends of the artificial intelligence era.
- Covers 5 major categories of Image, Text, Audio, Video, and Industrial application, and supports **one-click prediction**, **easy service deployment** and **transfer learning**
- All models are **OPEN SOURCE**, **FREE** to download and use them in offline scenario.
### Recent updates
-**2021.04.27:** The v2.1.0 version is released. **[Improvements]** Add supports for five new models, including two high-precision semantic segmentation models based on VOC dataset and three voice classification models. Enforce the transfer learning capabilities for image semantic segmentation, text semantic matching and voice classification on related datasets. **[Upgrades of deployment capabilities]** Add the export function APIs for two kinds of model formats, i.,e, ONNX and PaddleInference. **Important Open-Source Ecological Cooperation:** add the support for [BentoML](https://github.com/bentoml/BentoML/), which is a cloud native framework for serving deployment. Users can easily serve pre-trained models from PaddleHub by following the [Tutorial notebooks](https://github.com/PaddlePaddle/PaddleHub/blob/release/v2.1/demo/serving/bentoml/cloud-native-model-serving-with-bentoml.ipynb). Also, see this announcement and [Release note](https://github.com/bentoml/BentoML/releases/tag/v0.12.1) from BentoML. (Many thanks to @[parano](https://github.com/parano) @[cqvu](https://github.com/cqvu) @[deehrlic](https://github.com/deehrlic) for contributing this feature in PaddleHub). **[Bug fixes]**[#7da1230](https://github.com/PaddlePaddle/PaddleHub/commit/7da12302dd77e3d739da72821d41715ad8a7c79c) Fixed the problem that the model cannot resume training if metrics is not recorded. [#b0b3144](https://github.com/PaddlePaddle/PaddleHub/commit/b0b3144eff34e47cac8fc450c8b7cb6c557f9b84) Fixed the problem that the thread did not exit normally when the evaluation process was abnormal. [#30aace4](https://github.com/PaddlePaddle/PaddleHub/commit/30aace46414bbeef02beb75b7128f48fada82150) Improve the model installation process. The total number of pre-trained models reaches **【300】**.
-**2021.02.18:** The v2.0.0 version is released, making model development and debugging easier, and the finetune task is more flexible and easy to use.The ability to transfer learning for visual tasks is fully upgraded, supporting various tasks such as image classification, image coloring, and style transfer; Transformer models such as BERT, ERNIE, and RoBERTa are upgraded to dynamic graphs, supporting Fine-Tune capabilities for text classification and sequence labeling; Optimize the Serving capability, support multi-card prediction, automatic load balancing, and greatly improve performance; the new automatic data enhancement capability Auto Augment can efficiently search for data enhancement strategy combinations suitable for data sets. 61 new word vector models were added, including 51 Chinese models and 10 English models; add 4 image segmentation models, 2 depth models, 7 image generation models, and 3 text generation models, the total number of pre-trained models reaches **【274】**.
-**2020.12.1:** Release 2.0-beta1 version, migrate ERNIE, RoBERTa, BERT to dynamic graph mode. Add text classification fine-tune task based on large-scale pre-trained models.
-**2020.11.20:** Release 2.0-beta version, fully migrate the dynamic graph programming mode, and upgrade the service deployment Serving capability; add 1 hand key point detection model, 12 image cartoonization models, 3 image editing models, 3 speech synthesis models, syntax Analyzing one, the total number of pre-trained models reaches **【182】**.
-**2020.10.09:** Added 4 new OCR multi-language series models, 4 image editing models, and the total number of pre-trained models reached **【162】**.
-**2020.09.27:** 6 new text generation models and 1 image segmentation model were added, and the total number of pre-trained models reached **【154】**.
-**2020.08.13:** Released v1.8.1, added a segmentation model, and supports EMNLP2019-Sentence-BERT as a text matching task network. The total number of pre-training models reaches **【147】**.
-**2020.07.29:** Release v1.8.0, new AI couplets and AI writing poems, jieba word segmentation, LDA topic model, semantic similarity calculation, new target detection, short video classification model, ultra-lightweight Chinese and English OCR, new pedestrian detection, vehicle industrial-grade models such as detection and animal recognition support [VisualDL](https://github.com/PaddlePaddle/VisualDL) visualization training, and the total number of pre-training models reaches **【135】**.
## Features
## Introduction and Features
- PaddleHub aims to provide developers with rich, high-quality, and directly usable pre-trained models.
-**Abundant Pre-trained Models**: 300+ pre-trained models covering the 5 major categories including Image, Text, Audio, Video, and Industrial application. All of them are free for download and offline usage.
-**No need for deep learning background**: you can use AI models quickly and enjoy the dividends of the artificial intelligence era.
-**Quick Model Prediction**: Model prediction can be realized through a few lines of scripts to quickly experience the model effect.
-**Model As Service**: A one-line command to build deep learning model API service deployment capabilities.
-**Easy-to-use Transfer Learning**: Just few lines of code you can complete the transfer-learning task like image classification and text classification based on high quality pre-trained models.
-**Cross-platform**: Can run on Linux, Windows, MacOS and other operating systems.
## Visualization Demo
### Text Recognition
- Contain ultra-lightweight Chinese and English OCR models, high-precision Chinese and English, multilingual German, French, Japanese, Korean OCR recognition.
- Many thanks to CopyRight@[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) for the pre-trained models, you can try to train your models with PadddleOCR.
- Including face detection, mask face detection, multiple algorithms are optional.
- Many thanks to CopyRight@[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) for the pre-trained models, you can try to train your models with PadddleDetection.
-**Model As Service**: one-line command to build deep learning model API service deployment capabilities.
-**Easy-to-use Transfer Learning**: few lines of code to complete the transfer-learning task such as image classification and text classification based on high quality pre-trained models.
-**Cross-platform**: support Linux, Windows, MacOS and other operating systems.
### Image Editing
- 4x super resolution effect, multiple super resolution models are optional.
- Colorization models can be used to repair old grayscale photos.
- Many thanks to CopyRight@[PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN) for the pre-trained models, you can try to train your models with PadddleGAN.
-**2021.04.27:** The v2.1.0 version is released. [1] Add supports for five new models, including two high-precision semantic segmentation models based on VOC dataset and three voice classification models. [2] Enforce the transfer learning capabilities for image semantic segmentation, text semantic matching and voice classification on related datasets. [3] Add the export function APIs for two kinds of model formats, i.,e, ONNX and PaddleInference. [4] Add the support for [BentoML](https://github.com/bentoml/BentoML/), which is a cloud native framework for serving deployment. Users can easily serve pre-trained models from PaddleHub by following the [Tutorial notebooks](https://github.com/PaddlePaddle/PaddleHub/blob/release/v2.1/demo/serving/bentoml/cloud-native-model-serving-with-bentoml.ipynb). Also, see this announcement and [Release note](https://github.com/bentoml/BentoML/releases/tag/v0.12.1) from BentoML. (Many thanks to @[parano](https://github.com/parano) @[cqvu](https://github.com/cqvu) @[deehrlic](https://github.com/deehrlic) for contributing this feature in PaddleHub). [5] The total number of pre-trained models reaches **【300】**.
-**2021.02.18:** The v2.0.0 version is released, making model development and debugging easier, and the finetune task is more flexible and easy to use.The ability to transfer learning for visual tasks is fully upgraded, supporting various tasks such as image classification, image coloring, and style transfer; Transformer models such as BERT, ERNIE, and RoBERTa are upgraded to dynamic graphs, supporting Fine-Tune capabilities for text classification and sequence labeling; Optimize the Serving capability, support multi-card prediction, automatic load balancing, and greatly improve performance; the new automatic data enhancement capability Auto Augment can efficiently search for data enhancement strategy combinations suitable for data sets. 61 new word vector models were added, including 51 Chinese models and 10 English models; add 4 image segmentation models, 2 depth models, 7 image generation models, and 3 text generation models, the total number of pre-trained models reaches **【274】**.
-[【more】](./docs/docs_en/release.md)
### Image Generation
- Including portrait cartoonization, street scene cartoonization, and style transfer.
- Many thanks to CopyRight@[PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN)、CopyRight@[AnimeGAN](https://github.com/TachibanaYoshino/AnimeGANv2)for the pre-trained models.
- Pedestrian detection, vehicle detection, and more industrial-grade ultra-large-scale pretrained models are provided.
- Many thanks to CopyRight@[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) for the pre-trained models, you can try to train your models with PadddleDetection.
- High quality pixel-level portrait cutout model, ACE2P human body analysis world champion models are provided, Dynamic Sky Replacement and Harmonization.
- Many thanks to CopyRight@[PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg), CopyRight@[Zhengxia Zou](https://github.com/jiupinjia/SkyAR) for the pre-trained models, you can try to retrain your models by paddleseg or sky matting model.
- Many thanks to CopyRight@[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)、[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)、[PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN)、[AnimeGAN](https://github.com/TachibanaYoshino/AnimeGANv2)、[openpose](https://github.com/CMU-Perceptual-Computing-Lab/openpose)、[PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg)、[Zhengxia Zou](https://github.com/jiupinjia/SkyAR) for the pre-trained models, you can try to train your models with them.
- Many thanks to CopyRight@[ERNIE](https://github.com/PaddlePaddle/ERNIE)、[LAC](https://github.com/baidu/LAC)、[DDParser](https://github.com/baidu/DDParser)for the pre-trained models, you can try to train your models with them.
### Image Classification
- Various models like animal classification, dish classification, wild animal product classification are available.
- Many thanks to CopyRight@[PaddleClas](https://github.com/PaddlePaddle/PaddleClas) for the pre-trained models, you can try to train your models with PadddleClas.
- TTS speech synthesis algorithm, multiple algorithms are available.
- Many thanks to CopyRight@[Parakeet](https://github.com/PaddlePaddle/Parakeet) for the pre-trained models, you can try to train your models with Parakeet.
- Input: `Life was like a box of chocolates, you never know what you're gonna get.`
...
...
@@ -199,7 +94,7 @@ English | [简体中文](README_ch.md)
</table>
</div>
### Video Classification
### Video (8 models)
- Short video classification trained via large-scale video datasets, supports 3000+ tag types prediction for short Form Videos.
- Many thanks to CopyRight@[PaddleVideo](https://github.com/PaddlePaddle/PaddleVideo) for the pre-trained model, you can try to train your models with PaddleVideo.
-`Example: Input a short video of swimming, the algorithm can output the result of "swimming"`
...
...
@@ -224,49 +119,22 @@ If you have any questions during the use of the model, you can join the official
</div>
If you fail to scan the code, please add WeChat 15704308458 and note "Hub", the operating class will invite you to join the group.
- Contain ultra-lightweight Chinese and English OCR models, high-precision Chinese and English, multilingual German, French, Japanese, Korean OCR recognition.
- Many thanks to CopyRight@[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) for the pre-trained models, you can try to train your models with PadddleOCR.
- Including face detection, mask face detection, multiple algorithms are optional.
- Many thanks to CopyRight@[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) for the pre-trained models, you can try to train your models with PadddleDetection.
- 4x super resolution effect, multiple super resolution models are optional.
- Colorization models can be used to repair old grayscale photos.
- Many thanks to CopyRight@[PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN) for the pre-trained models, you can try to train your models with PadddleGAN.
- Including portrait cartoonization, street scene cartoonization, and style transfer.
- Many thanks to CopyRight@[PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN)、CopyRight@[AnimeGAN](https://github.com/TachibanaYoshino/AnimeGANv2)for the pre-trained models.
- Pedestrian detection, vehicle detection, and more industrial-grade ultra-large-scale pretrained models are provided.
- Many thanks to CopyRight@[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) for the pre-trained models, you can try to train your models with PadddleDetection.
- High quality pixel-level portrait cutout model, ACE2P human body analysis world champion models are provided, Dynamic Sky Replacement and Harmonization.
- Many thanks to CopyRight@[PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg), CopyRight@[Zhengxia Zou](https://github.com/jiupinjia/SkyAR) for the pre-trained models, you can try to retrain your models by paddleseg or sky matting model.
(The second gif comes from CopyRight@[jiupinjia/SkyAR](https://github.com/jiupinjia/SkyAR#district-9-ship-video-source))
</div>
### Image Classification
- Various models like animal classification, dish classification, wild animal product classification are available.
- Many thanks to CopyRight@[PaddleClas](https://github.com/PaddlePaddle/PaddleClas) for the pre-trained models, you can try to train your models with PadddleClas.
- TTS speech synthesis algorithm, multiple algorithms are available.
- Many thanks to CopyRight@[Parakeet](https://github.com/PaddlePaddle/Parakeet) for the pre-trained models, you can try to train your models with Parakeet.
- Input: `Life was like a box of chocolates, you never know what you're gonna get.`
- Short video classification trained via large-scale video datasets, supports 3000+ tag types prediction for short Form Videos.
- Many thanks to CopyRight@[PaddleVideo](https://github.com/PaddlePaddle/PaddleVideo) for the pre-trained model, you can try to train your models with PaddleVideo.
-`Example: Input a short video of swimming, the algorithm can output the result of "swimming"`
