From 79a6419f267c7fa5c4015ef129aed49b3a683939 Mon Sep 17 00:00:00 2001 From: LielinJiang <50691816+LielinJiang@users.noreply.github.com> Date: Wed, 8 Dec 2021 18:28:51 +0800 Subject: [PATCH] Add release note 2.1.0 (#515) * add release note 2.1.0 --- README.md | 37 +++++++++++++++++++++----- README_cn.md | 23 +++++++++++++--- docs/en_US/tutorials/motion_driving.md | 6 ++--- ppgan/version.py | 2 +- requirements.txt | 1 + 5 files changed, 55 insertions(+), 14 deletions(-) diff --git a/README.md b/README.md index d9ff2c7..e35ed86 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ GAN-Generative Adversarial Network, was praised by "the Father of Convolutional
- + - 👩‍🚀 **A Space Odyssey ：[LapStyle](./docs/zh_CN/tutorials/lap_style.md) image translation take you travel around the universe**👨‍🚀 - **[Online Toturials](https://aistudio.baidu.com/aistudio/projectdetail/2343740?contributionType=1)** @@ -51,7 +51,7 @@ GAN-Generative Adversarial Network, was praised by "the Father of Convolutional
- + - **💞 Add Face Morphing function💞 : you can perfectly merge any two faces and make the new face get any facial expressions!** - Tutorials: https://aistudio.baidu.com/aistudio/projectdetail/2254031 @@ -61,10 +61,10 @@ GAN-Generative Adversarial Network, was praised by "the Father of Convolutional - **Publish a new version of First Oder Motion model by having two impressive features:** - - High resolution 512x512 + - High resolution 512x512 - Face Enhancement - - Tutorials: https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/zh_CN/tutorials/motion_driving.md - + - Tutorials: https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/zh_CN/tutorials/motion_driving.md + - **New image translation ability--transfer photo into oil painting style:** - Complete tutorials for deployment: https://github.com/wzmsltw/PaintTransformer @@ -77,7 +77,7 @@ GAN-Generative Adversarial Network, was praised by "the Father of Convolutional #### **Installation** -* Environment dependence: +* Environment dependence: - PaddlePaddle >= 2.1.0 - Python >= 3.6 - CUDA >= 10.1 @@ -124,7 +124,7 @@ You can run those projects in the [AI Studio](https://aistudio.baidu.com/aistudi ## Examples -### Face Morphing +### Face Morphing
@@ -199,6 +199,29 @@ You can run those projects in the [AI Studio](https://aistudio.baidu.com/aistudi ## Changelog +- v2.1.0 (2021.12.8) + - Release a video super-resolution model PP-MSVSR and multiple pre-training weights + - Release several SOTA video super-resolution models and their pre-trained models such as BasicVSR, IconVSR and BasicVSR++ + - Release the light-weight motion-driven model(Volume compression: 229M->10.1M), and optimized the fusion effect + - Release high-resolution FOMM and Wav2Lip pre-trained models + - Release several interesting applications based on StyleGANv2, such as face inversion, face fusion and face editing + - Released Baidu’s self-developed and effective style transfer model LapStyle and its interesting applications, and launched the official website [experience page](https://www.paddlepaddle.org.cn/paddlegan) + - Release a light-weight image super-resolution model PAN + +- v2.0.0 (2021.6.2) + - Release [Fisrt Order Motion](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/en_US/tutorials/motion_driving.md) model and multiple pre-training weights + - Release applications that support [Multi-face action driven](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/en_US/tutorials/motion_driving.md#1-test-for-face) + - Release video super-resolution model [EDVR](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/en_US/tutorials/video_super_resolution.md) and multiple pre-training weights + - Release the contents of [7-day punch-in training camp](https://github.com/PaddlePaddle/PaddleGAN/tree/develop/education) corresponding to PaddleGAN + - Enhance the robustness of PaddleGAN running on the windows platform + +- v2.0.0-beta (2021.3.1) + - Completely switch the API of Paddle 2.0.0 version. + - Release of super-resolution models: ESRGAN, RealSR, LESRCNN, DRN, etc. + - Release lip migration model: Wav2Lip + - Release anime model of Street View: AnimeGANv2 + - Release face animation model: U-GAT-IT, Photo2Cartoon + - Release SOTA generation model: StyleGAN2 - v0.1.0 (2020.11.02) - Release first version, supported models include Pixel2Pixel, CycleGAN, PSGAN. Supported applications include video frame interpolation, super resolution, colorize images and videos, image animation. diff --git a/README_cn.md b/README_cn.md index 2438563..02c083a 100644 --- a/README_cn.md +++ b/README_cn.md @@ -27,7 +27,7 @@ GAN--生成对抗网络，被“卷积网络之父”**Yann LeCun（杨立昆） - **报名链接💡：https://paddleqiyeban.wjx.cn/vj/tKidSqZ.aspx?udsid=453804** ⭐ **扫码加入技术交流群** ⭐ - +
@@ -45,8 +45,8 @@ GAN--生成对抗网络，被“卷积网络之父”**Yann LeCun（杨立昆） **想要看直播回放视频请点击链接：https://www.bilibili.com/video/BV1GZ4y1g7xc** ## 产品动态 -- 💛 **最新发布** 💛 - +- 💛 **最新发布** 💛 + 👀 **视频超分SOTA算法[PP-MSVSR](./docs/zh_CN/tutorials/video_super_resolution.md)：一行命令从"马赛克"到"高清影像"** 👀
@@ -229,6 +229,14 @@ GAN--生成对抗网络，被“卷积网络之父”**Yann LeCun（杨立昆） ## 版本更新 +- v2.1.0 (2021.12.8) + - 发布视频超分辨率模型PP-MSVSR以及多个预训练权重 + - 发布BasicVSR，IconVSR与Basicvsr++等多个效果领先的视频超分辨率模型及其预训练模型 + - 发布轻量级动作驱动模型（体积压缩：229M->10.1M），并优化融合效果 + - 发布高分辨率的FOMM和Wav2Lip预训练模型 + - 发布人脸反演，人脸融合和人脸编辑等多个基于StyleGANv2的有趣应用 + - 发布百度自研且效果领先的风格迁移模型LapStyle及其有趣应用，并上线官网[体验页面](https://www.paddlepaddle.org.cn/paddlegan) + - 发布轻量的图像超分辨模型PAN - v2.0.0 (2021.6.2) - 发布[Fisrt Order Motion](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/en_US/tutorials/motion_driving.md)模型以及多个预训练权重 @@ -236,6 +244,15 @@ GAN--生成对抗网络，被“卷积网络之父”**Yann LeCun（杨立昆） - 发布视频超分辨模型[EDVR](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/en_US/tutorials/video_super_resolution.md)以及多个预训练权重 - 发布PaddleGAN对应的[七日打卡训练营](https://github.com/PaddlePaddle/PaddleGAN/tree/develop/education)内容 - 增强PaddleGAN在windows平台运行的鲁棒性 + +- v2.0.0-beta (2021.3.1) + - 完全切换Paddle 2.0.0版本的API。 + - 发布超分辨模型：ESRGAN，RealSR，LESRCNN，DRN等 + - 发布唇形迁移模型：Wav2Lip + - 发布街景动漫化模型：AnimeGANv2 + - 发布人脸动漫化模型：U-GAT-IT ，Photo2Cartoon + - 发布高清人脸生成模型：StyleGAN2 + - v0.1.0 (2020.11.02) - 初版发布，支持Pixel2Pixel、CycleGAN、PSGAN模型，支持视频插针、超分、老照片/视频上色、视频动作生成等应用。 - 模块化设计，接口简单易用。 diff --git a/docs/en_US/tutorials/motion_driving.md b/docs/en_US/tutorials/motion_driving.md index 9fb64f0..9f8fc2e 100644 --- a/docs/en_US/tutorials/motion_driving.md +++ b/docs/en_US/tutorials/motion_driving.md @@ -31,7 +31,7 @@ The proposed method is not exclusively for facial expression transfer, it also s At the same time, PaddleGAN also provides a ["faceutils" tool](https://github.com/PaddlePaddle/PaddleGAN/tree/develop/ppgan/faceutils) for face-related work, including face detection, face segmentation, keypoints detection, etc. -- #### Face Enhancement +- #### Face Enhancement - **This effect significantly improves the definition of the driven video.** @@ -154,8 +154,8 @@ Currently, we use mobilenet combined with pruning to compress models, see the co | | Size(M) | reconstruction loss | | ---------- | ------- | ------------------- | -| Original | 229 | 0.012058867 | -| Compressed | 6.1 | 0.015025159 | +| Original | 229 | 0.041781392 | +| Compressed | 10.1 | 0.047878753 | **Training:** First, set mode in configs/firstorder_vox_mobile_256.yaml as kp_detector, train the compressed kp_detector model, and immobilize the original generator model. Then set mode in configs/firstorder_vox_mobile_256.yaml as generator，train the compressed generator model, and immobilize the original kp_detector model. Finally, set mode as both and modify kp_weight_path and gen_weight_path in the config to the path of trained model to train together。 diff --git a/ppgan/version.py b/ppgan/version.py index 7ec66af..9d8d23a 100644 --- a/ppgan/version.py +++ b/ppgan/version.py @@ -12,4 +12,4 @@ # See the License for the specific language governing permissions and # limitations under the License. -ppgan_version = '2.0.0' +ppgan_version = '2.1.0' diff --git a/requirements.txt b/requirements.txt index 51459e7..a8dda25 100644 --- a/requirements.txt +++ b/requirements.txt @@ -10,3 +10,4 @@ numba==0.53.1 easydict munch natsort +matplotlib -- GitLab