You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: README_en.md
+13-6
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
## Introduction
4
4
5
-
**PaddleYOLO** is a YOLO Series toolbox based on [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection), **only relevant codes of YOLO series models are included**. It supports `YOLOv3`,`PP-YOLO`,`PP-YOLOv2`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6`,`YOLOv7`,`YOLOv8`,`RTMDet` and so on, see COCO dataset ModelZoo in [ModelZoo](docs/MODEL_ZOO_en.md) and [configs](configs/).
5
+
**PaddleYOLO** is a YOLO series toolbox based on [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection), **only relevant codes of YOLO series models are included**. It supports `YOLOv3`,`PP-YOLO`,`PP-YOLOv2`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6`,`YOLOv7`,`YOLOv8`,`YOLOv5u`,`YOLOv7u`,`RTMDet` and so on, see COCO dataset ModelZoo in [ModelZoo](docs/MODEL_ZOO_en.md) and [configs](configs/).
- Please refer to [doc](docs/MODEL_ZOO_en.md#CustomDataset) and [issue](https://github.com/PaddlePaddle/PaddleYOLO/issues/43).
115
-
- PaddleDetection team provides various **feature detection models based on PP-YOLOE** , which can also be used as a reference to modify on your custom dataset. Please refer to [PP-YOLOE application](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ppyoloe/application), [pphuman](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/pphuman), [ppvehicle](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ppvehicle), [visdrone](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/visdrone) and [smalldet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/smalldet).
116
-
- PaddleDetection also provides **various YOLO models for VOC dataset** , which can also be used as a reference to modify on your custom dataset. Please refer to [voc](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc).
115
+
- PaddleDetection team provides various **feature detection models based on PP-YOLOE** , which can also be used as a reference to modify on your custom dataset. Please refer to [PP-YOLOE application](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.6/configs/ppyoloe/application), [pphuman](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.6/configs/pphuman), [ppvehicle](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.6/configs/ppvehicle), [visdrone](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.6/configs/visdrone) and [smalldet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.6/configs/smalldet).
116
+
- PaddleDetection also provides **various YOLO models for VOC dataset** , which can also be used as a reference to modify on your custom dataset. Please refer to [voc](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.6/configs/voc).
117
117
- Please **ensure the corresponding COCO trained weights are loaded as pre-train weights** at first. Set the `pretrain_weights: ` with corresponding COCO trained weights in the config file, and it will generally prompt that the number of channels convolved by the head classification layer does not correspond, which is a normal phenomenon, because the number of types of user-defined data sets is generally inconsistent with that of COCO data sets.
118
118
- We recommend to use YOLO detection model **with a total `batch_size` at least greater than `64` to train**. If the resources are insufficient, please **use the smaller model** or **reduce the input size of the model**. To ensure high detection accuracy, **you'd better not try to using single GPU or total `batch_size` less than `64` for training**;
- Support `YOLOv8`,`YOLOv5u`,`YOLOv7u` inference and deploy.
138
+
- Support `Swin-Transformer`、`ViT`、`FocalNet` backbone to get high-precision version of `PP-YOLOE+`.
139
+
- Support `YOLOv8` in [FastDeploy](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/vision/detection/paddledetection).
- Release [PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO): support `YOLOv3`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6` and `YOLOv7`; support using `ConvNeXt` backbone to get high-precision version of `PP-YOLOE`,`YOLOX` and `YOLOv5`; support PaddleSlim accelerated quantitative training `PP-YOLOE`,`YOLOv5`,`YOLOv6` and `YOLOv7`.
1.For the annotation of custom dataset, please refer to [DetAnnoTools](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/tutorials/data/DetAnnoTools_en.md);
129
+
1.For the annotation of custom dataset, please refer to [DetAnnoTools](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.6/docs/tutorials/data/DetAnnoTools_en.md);
130
130
131
-
2.For training preparation of custom dataset，please refer to [PrepareDataSet](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/tutorials/data/PrepareDetDataSet_en.md).
131
+
2.For training preparation of custom dataset，please refer to [PrepareDataSet](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.6/docs/tutorials/data/PrepareDetDataSet_en.md).
In this demo, the model we used is based on [PP-PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/picodet). Because of the excellent performance, PP-PicoDet are very suitable for deployment on mobile or CPU. And it is released by [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection).
107
+
In this demo, the model we used is based on [PP-PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.6/configs/picodet). Because of the excellent performance, PP-PicoDet are very suitable for deployment on mobile or CPU. And it is released by [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection).
- For more CUDA version or environment to quick install, please refer to the [PaddlePaddle Quick Installation document](https://www.paddlepaddle.org.cn/install/quick)
0 commit comments