diff --git a/configs/picodet/README.md b/configs/picodet/README.md index 3db37244f0046f67b5aa0b6a5ba0349623cc2cfc..235b494e03845af9582f80cb55f51c34ebf5a9e7 100644 --- a/configs/picodet/README.md +++ b/configs/picodet/README.md @@ -3,13 +3,18 @@ ![](../../docs/images/picedet_demo.jpeg) ## Introduction -We developed a series of lightweight models, which named `PP-PicoDet`. Because of its excellent performance, it is very suitable for deployment on mobile or CPU. +We developed a series of lightweight models, which named `PP-PicoDet`. Because of its excellent performance, it is very suitable for deployment on mobile or CPU. For more details, please refer to our [report on arXiv](https://arxiv.org/abs/2111.00902). - 🌟 Higher mAP: the **first** object detectors that surpass mAP(0.5:0.95) **30+** within 1M parameters when the input size is 416. - 🚀 Faster latency: 150FPS on mobile ARM CPU. - 😊 Deploy friendly: support PaddleLite/MNN/NCNN/OpenVINO and provide C++/Python/Android implementation. - 😍 Advanced algorithm: use the most advanced algorithms and innovate, such as ESNet, CSP-PAN, SimOTA with VFL, etc. + +
+ +
+ ### Comming soon - [ ] More series of model, such as smaller or larger model. - [ ] Pretrained models for more scenarios. @@ -41,7 +46,7 @@ We developed a series of lightweight models, which named `PP-PicoDet`. Because o
Table Notes: -- Latency: All our models test on `Qualcomm Snapdragon 865(4\*A77+4\*A55)` with 4 threads by arm8 and with FP16. In the above table, test latency on [NCNN](https://github.com/Tencent/ncnn) and `Lite`->[Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite). And testing latency with code:[MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark). +- Latency: All our models test on `Qualcomm Snapdragon 865(4xA77+4xA55)` with 4 threads by arm8 and with FP16. In the above table, test latency on [NCNN](https://github.com/Tencent/ncnn) and `Lite`->[Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite). And testing latency with code: [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark). - PicoDet is trained on COCO train2017 dataset and evaluated on COCO val2017. - PicoDet used 4 or 8 GPUs for training and all checkpoints are trained with default settings and hyperparameters. @@ -123,7 +128,13 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco/ \ - [NCNN C++/Python demo](../../deploy/third_engine/demo_ncnn) - [MNN C++/Python demo](../../deploy/third_engine/demo_mnn) - [OpenVINO C++/Python demo](../../deploy/third_engine/demo_openvino) -- [Android demo]() +- [Android demo](https://github.com/JiweiMaster/PP-PicoDet-Android-Demo) + + +
+ +
+ ## Slim @@ -172,6 +183,13 @@ python tools/post_quant.py -c configs/picodet/picodet_s_320_coco.yml \ ## Cite PiocDet If you use PiocDet in your research, please cite our work by using the following BibTeX entry: ``` -comming soon +@misc{yu2021pppicodet, + title={PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices}, + author={Guanghua Yu and Qinyao Chang and Wenyu Lv and Chang Xu and Cheng Cui and Wei Ji and Qingqing Dang and Kaipeng Deng and Guanzhong Wang and Yuning Du and Baohua Lai and Qiwen Liu and Xiaoguang Hu and Dianhai Yu and Yanjun Ma}, + year={2021}, + eprint={2111.00902}, + archivePrefix={arXiv}, + primaryClass={cs.CV} +} ``` diff --git a/docs/images/picodet_android_demo1.jpg b/docs/images/picodet_android_demo1.jpg new file mode 100644 index 0000000000000000000000000000000000000000..6f5d2bc6716c2b3edf2fc9bda74756fafc53283d Binary files /dev/null and b/docs/images/picodet_android_demo1.jpg differ diff --git a/docs/images/picodet_android_demo2.jpg b/docs/images/picodet_android_demo2.jpg new file mode 100644 index 0000000000000000000000000000000000000000..3eb2d77f08d618a6160dcf74cb5447026aa8ad47 Binary files /dev/null and b/docs/images/picodet_android_demo2.jpg differ diff --git a/docs/images/picodet_android_demo3.jpg b/docs/images/picodet_android_demo3.jpg new file mode 100644 index 0000000000000000000000000000000000000000..f58d0510b7c17f523572d4d228cc9a8fa10c71df Binary files /dev/null and b/docs/images/picodet_android_demo3.jpg differ diff --git a/docs/images/picodet_android_demo4.jpg b/docs/images/picodet_android_demo4.jpg new file mode 100644 index 0000000000000000000000000000000000000000..c8c0dc128ed058c61434b7d7029d209ad64c3ac4 Binary files /dev/null and b/docs/images/picodet_android_demo4.jpg differ diff --git a/docs/images/picodet_map.png b/docs/images/picodet_map.png new file mode 100644 index 0000000000000000000000000000000000000000..0ed9ada22fdb5eb06ae384afd629149f4535be7f Binary files /dev/null and b/docs/images/picodet_map.png differ diff --git a/ppdet/modeling/tests/test_architectures.py b/ppdet/modeling/tests/test_architectures.py index 693a27e1af38c91833ccb481a1140f46882d32e1..25767e74abd9fce29c51adbc4b5109e17a50aa0b 100644 --- a/ppdet/modeling/tests/test_architectures.py +++ b/ppdet/modeling/tests/test_architectures.py @@ -62,7 +62,7 @@ class TestGFL(TestFasterRCNN): class TestPicoDet(TestFasterRCNN): def set_config(self): - self.cfg_file = 'configs/picodet/picodet_s_shufflenetv2_320_coco.yml' + self.cfg_file = 'configs/picodet/picodet_s_320_coco.yml' if __name__ == '__main__':