diff --git a/README_EN.md b/README_EN.md index 92bce8753..a8db39a30 100644 --- a/README_EN.md +++ b/README_EN.md @@ -32,35 +32,24 @@ Including image classification, object detection, image segmentation, face detec ## šŸ“£ Recent Updates -- šŸ”„怐Live Preview怑2022.11.09 20:30ļ½ž21:30ļ¼Œ*Covering the full spectrum of cloud-side scenarios with 150+ popular models for rapid deployment* -- šŸ”„怐Live Preview怑2022.11.10 20:30ļ½ž21:30ļ¼Œ*10+ AI hardware deployments from Rockchip, Amlogic, NXP and others, straight to industry landing* -- šŸ”„怐Live Preview怑2022.11.10 19:00ļ½ž20:00ļ¼Œ*10+ popular models deployed in RK3588, RK3568 in action* +- šŸ”„怐Live Preview怑2022.11.09~2022.11.10 China Standard Time, 20:30ļ½ž21:30ļ¼Œ Engineers@FastDeploy will show Using FastDeploy Efficiently for 3 days. - **Slack**ļ¼šJoin our [Slack community](https://join.slack.com/t/fastdeployworkspace/shared_invite/zt-1hhvpb279-iw2pNPwrDaMBQ5OQhO3Siw) and chat with other community members about ideas. - - **WeChat**ļ¼šScan the QR code below using WeChat, follow the PaddlePaddle official account and fill out the questionnaire to join the WeChat group + - **WeChat**ļ¼šScan the QR code below using WeChat, follow the PaddlePaddle official account and fill out the questionnaire to join the WeChat group.
- -- šŸ”„ **2022.10.31ļ¼šRelease FastDeploy [release v0.5.0](https://github.com/PaddlePaddle/FastDeploy/tree/release/0.5.0)**
+- šŸ”„ **2022.11.8ļ¼šRelease FastDeploy [release v0.6.0](https://github.com/PaddlePaddle/FastDeploy/tree/release/0.6.0)**
- **šŸ–„ļø Server-side and Cloud Deployment: Support more backend, Support more CV models** - - Support Paddle Inference TensorRT, and provide a seamless deployment experience with other inference engines include Paddle Inference态Paddle Lite态TensorRT态OpenVINO态ONNX Runtimeļ¼› - - Support Graphcore IPU through paddle Inference; - - Support tracking model [PP-Tracking](./examples/vision/tracking/pptracking) and [RobustVideoMatting](./examples/vision/matting) modelļ¼› - - Support [one-click model quantization](tools/quantization) to improve model inference speed by 1.5 to 2 times on CPU & GPU platform. The supported quantized model are YOLOv7, YOLOv6, YOLOv5, etc. - -- šŸ”„ **2022.10.24ļ¼šRelease FastDeploy [release v0.4.0](https://github.com/PaddlePaddle/FastDeploy/tree/release/0.4.0)**
- - **šŸ–„ļø Server-side and Cloud Deployment: end-to-end optimization, Support more CV and NLP model** - - end-to-end optimization on GPU, [YOLO series](examples/vision/detection) model end-to-end inference speedup from 43ms to 25ms; - - Support CV models include PP-OCRv3, PP-OCRv2, PP-TinyPose, PP-Matting, etc. and provides [end-to-end deployment demos](examples/vision/detection/); - - Support information extraction model is UIE, and provides [end-to-end deployment demos](examples/text/uie); - - Support [TinyPose](examples/vision/keypointdetection/tiny_pose) and [PicoDet and TinyPose](examples/vision/keypointdetection/det_keypoint_unite)Pipeline deployment. + - 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态GPU memory usage of Paddle Inference态TensorRT态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. - **šŸ“± Mobile and Edge Device Deployment: support new backendļ¼Œsupport more CV model** - - Integrate Paddle Lite and provide a seamless deployment experience with other inference engines include TensorRT态OpenVINO态ONNX Runtime态Paddle Inferenceļ¼› - - Support [Lightweight Detection Model](examples/vision/detection/paddledetection/android) and [classification model](examples/vision/classification/paddleclas/android) on Android Platformļ¼ŒDownload to try it out. - - **šŸŒ Browser Deployment: support more CV model** - - Browser deployment and Mini Program deployment New [OCR and other CV models](examples/application/js) capability. - + - Support RKNPU2, and provide a seamless deployment experience with other inference engines include Paddle Inference态Paddle Inference TensorRT态Paddle Lite态TensorRT态OpenVINO态ONNX Runtimeļ¼› + - Support [PP-HumanSeg态Unet](examples/vision/segmentation/paddleseg/rknpu2)态[PicoDet](./examples/vision/detection/paddledetection/rknpu2)态[SCRFD](./examples/vision/facedet/scrfd/rknpu2) and other popular models on NPU. + +- [**more releases information**](./releases) ## Contents