apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Update README_EN.md

Browse Source
This commit is contained in:
leiqing
2022-11-21 10:53:29 +08:00
committed by GitHub
parent 10ac610df6
commit f1b048d239
1 changed files with 10 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
README_EN.md
View File

@@ -45,15 +45,17 @@ Including image classification, object detection, image segmentation, face detec
<img src="https://user-images.githubusercontent.com/54695910/200145290-d5565d18-6707-4a0b-a9af-85fd36d35d13.jpg" width = "120" height = "120" />
</div>
- 🔥 **2022.11.8：Release FastDeploy [release v0.6.0](https://github.com/PaddlePaddle/FastDeploy/tree/release/0.6.0)** <br>
- **🖥️ Server-side and Cloud Deployment: Support more backend, Support more CV models**
- Optimize preprocessing and postprocessing memory creation logic on YOLO series, PaddleClas, PaddleDetection;
- Integrate visual preprocessing operations, optimize the preprocessing performance of PaddleClas and PaddleDetection, and improve end-to-end performance;
- Add Clone interface support for service-based deployment, reducing the memory、GPU memory usage of Paddle Inference、TensorRT、OpenVINO backend in multiple instances
- Support [FSANet](./examples/vision/headpose) head pose recognition model, [PFLD](./examples/vision/facealign) face alignment model, [ERNIE](./examples/text/ernie-3.0) text classification model etc.
- 🔥 **2022.11.15：Release FastDeploy [release v0.7.0](https://github.com/PaddlePaddle/FastDeploy/tree/release/0.7.0)** <br>
- **🖥️ Server-side and Cloud Deployment: Support more CV models, improve deployment performance**
- Support [PaddleClas](./examples/vision/classification/paddleclas/serving) model service-based deployment；
- Support [Stable Diffusion](./examples/multimodal/stable_diffusion) model deployment；
- Upgrade PaddleClas、PaddleDetection、YOLOv5 deployment code to support predict and batch_predict;
- Add the Pad function operator for the FDTensor to support Padding of the input during batch prediction;
- Add Python API to_dlpack interface for FDTensor to support copyless transfer of FDTensor between frameworks.;
- **📱 Mobile and Edge Device Deployment: support new backend，support more CV model**
- Support RKNPU2, and provide a seamless deployment experience with other inference engines include Paddle Inference、Paddle Inference TensorRT、Paddle Lite、TensorRT、OpenVINO、ONNX Runtime；
- Support [PP-HumanSeg、Unet](examples/vision/segmentation/paddleseg/rknpu2)、[PicoDet](./examples/vision/detection/paddledetection/rknpu2)、[SCRFD](./examples/vision/facedet/scrfd/rknpu2) and other popular models on NPU.
- Support Paddle Lite TIM-VX for supporting hardware such as Rockchip RV1109,RV1126, RK1808, Amlogic A311D, etc. And provide a seamless deployment experience with other inference engines include Paddle Inference、Paddle Inference TensorRT、Paddle Lite、TensorRT、OpenVINO、ONNX Runtime、RKNPU2;
- support Image classification model [ResNet50_vd](./examples/vision/classification/paddleclas/rk1126/cpp) on Rockchip RV1126;
- support Face detection model [SCRFD](./examples/vision/facedet/scrfd/rknpu2) on Rockchip RK3588, RK3568 and other hardware;
- [**more releases information**](./releases)