[YOLOv8] Add PaddleYOLOv8 models download links (#1152)

* [Model] Support PaddleYOLOv8 model * [YOLOv8] Add PaddleYOLOv8 pybind * [Other] update from latest develop (#30) * [Backend] Remove all lite options in RuntimeOption (#1109) * Remove all lite options in RuntimeOption * Fix code error * move pybind * Fix build error * [Backend] Add TensorRT FP16 support for AdaptivePool2d (#1116) * add fp16 cuda kernel * fix code bug * update code * [Doc] Fix KunlunXin doc (#1139) fix kunlunxin doc * [Model] Support PaddleYOLOv8 model (#1136) Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> * [YOLOv8] add PaddleYOLOv8 pybind11 (#1144) (#31) * [Model] Support PaddleYOLOv8 model * [YOLOv8] Add PaddleYOLOv8 pybind * [Other] update from latest develop (#30) * [Backend] Remove all lite options in RuntimeOption (#1109) * Remove all lite options in RuntimeOption * Fix code error * move pybind * Fix build error * [Backend] Add TensorRT FP16 support for AdaptivePool2d (#1116) * add fp16 cuda kernel * fix code bug * update code * [Doc] Fix KunlunXin doc (#1139) fix kunlunxin doc * [Model] Support PaddleYOLOv8 model (#1136) Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> * [benchmark] add PaddleYOLOv8 -> benchmark * [benchmark] add PaddleYOLOv8 -> benchmark * [Lite] Support PaddleYOLOv8 with Lite Backend * [Pick] Update from latest develop (#32) * [Model] Support Insightface model inferenceing on RKNPU (#1113) * 更新交叉编译 * 更新交叉编译 * 更新交叉编译 * 更新交叉编译 * 更新交叉编译 * 更新交叉编译 * 更新交叉编译 * 更新交叉编译 * 更新交叉编译 * Update issues.md * Update fastdeploy_init.sh * 更新交叉编译 * 更新insightface系列模型的rknpu2支持 * 更新insightface系列模型的rknpu2支持 * 更新说明文档 * 更新insightface * 尝试解决pybind问题 Co-authored-by: Jason <928090362@qq.com> Co-authored-by: Jason <jiangjiajun@baidu.com> * [Other] Add Function For Aligning Face With Five Points (#1124) * 更新5点人脸对齐的代码 * 更新代码格式 * 解决comment * update example * 更新注释 Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> * [Lite] Support PaddleYOLOv8 with Lite Backend (#1145) * [Model] Support PaddleYOLOv8 model * [YOLOv8] Add PaddleYOLOv8 pybind * [Other] update from latest develop (#30) * [Backend] Remove all lite options in RuntimeOption (#1109) * Remove all lite options in RuntimeOption * Fix code error * move pybind * Fix build error * [Backend] Add TensorRT FP16 support for AdaptivePool2d (#1116) * add fp16 cuda kernel * fix code bug * update code * [Doc] Fix KunlunXin doc (#1139) fix kunlunxin doc * [Model] Support PaddleYOLOv8 model (#1136) Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> * [YOLOv8] add PaddleYOLOv8 pybind11 (#1144) (#31) * [Model] Support PaddleYOLOv8 model * [YOLOv8] Add PaddleYOLOv8 pybind * [Other] update from latest develop (#30) * [Backend] Remove all lite options in RuntimeOption (#1109) * Remove all lite options in RuntimeOption * Fix code error * move pybind * Fix build error * [Backend] Add TensorRT FP16 support for AdaptivePool2d (#1116) * add fp16 cuda kernel * fix code bug * update code * [Doc] Fix KunlunXin doc (#1139) fix kunlunxin doc * [Model] Support PaddleYOLOv8 model (#1136) Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> * [benchmark] add PaddleYOLOv8 -> benchmark * [benchmark] add PaddleYOLOv8 -> benchmark * [Lite] Support PaddleYOLOv8 with Lite Backend Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> * [Model] Add Silero VAD example (#1107) * add vad example * fix typo * fix typo * rename file * remove model and wav * delete Vad.cc * delete Vad.h * rename and format * fix max and min * update readme * rename var * format * add params * update readme * update readme * Update README.md * Update README_CN.md Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: Zheng-Bicheng <58363586+Zheng-Bicheng@users.noreply.github.com> Co-authored-by: Jason <928090362@qq.com> Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> Co-authored-by: Qianhe Chen <54462604+chenqianhe@users.noreply.github.com> * [YOLOv8] Support PaddleYOLOv8 on Kunlunxin&Ascend * [YOLOv8] Add PaddleYOLOv8 model download links * [YOLOv8] Add PaddleYOLOv8 Box AP Co-authored-by: Jason <jiangjiajun@baidu.com> Co-authored-by: yeliang2258 <30516196+yeliang2258@users.noreply.github.com> Co-authored-by: Zheng-Bicheng <58363586+Zheng-Bicheng@users.noreply.github.com> Co-authored-by: Jason <928090362@qq.com> Co-authored-by: Qianhe Chen <54462604+chenqianhe@users.noreply.github.com>
2025-10-05 16:48:03 +08:00 · 2023-01-16 13:15:24 +08:00
parent 4393520a87
commit 30def02a89
5 changed files with 74 additions and 7 deletions
--- a/benchmark/benchmark_ppdet.py
+++ b/benchmark/benchmark_ppdet.py
@@ -43,17 +43,22 @@ def parse_arguments():
    parser.add_argument(
        "--device",
        default="cpu",
-        help="Type of inference device, support 'cpu' or 'gpu'.")
+        help="Type of inference device, support 'cpu', 'gpu', 'kunlunxin', 'ascend' etc.")
    parser.add_argument(
        "--backend",
        type=str,
        default="default",
-        help="inference backend, default, ort, ov, trt, paddle, paddle_trt.")
+        help="inference backend, default, ort, ov, trt, paddle, paddle_trt, lite.")
    parser.add_argument(
        "--enable_trt_fp16",
        type=ast.literal_eval,
        default=False,
        help="whether enable fp16 in trt backend")
+    parser.add_argument(
+        "--enable_lite_fp16",
+        type=ast.literal_eval,
+        default=False,
+        help="whether enable fp16 in lite backend")    
    parser.add_argument(
        "--enable_collect_memory_info",
        type=ast.literal_eval,
@@ -68,6 +73,7 @@ def build_option(args):
    device = args.device
    backend = args.backend
    enable_trt_fp16 = args.enable_trt_fp16
+    enable_lite_fp16 = args.enable_lite_fp16
    option.set_cpu_thread_num(args.cpu_num_thread)
    if device == "gpu":
        option.use_gpu()
@@ -111,9 +117,35 @@ def build_option(args):
            raise Exception(
                "While inference with CPU, only support default/ort/ov/paddle now, {} is not supported.".
                format(backend))
+    elif device == "kunlunxin":
+        option.use_kunlunxin()
+        if backend == "lite":
+            option.use_lite_backend()
+        elif backend == "ort":
+            option.use_ort_backend()
+        elif backend == "paddle":
+            option.use_paddle_backend()
+        elif backend == "default":
+            return option
+        else:
+            raise Exception(
+                "While inference with CPU, only support default/ort/lite/paddle now, {} is not supported.".
+                format(backend))    
+    elif device == "ascend":
+        option.use_ascend()
+        if backend == "lite":
+            option.use_lite_backend()
+            if enable_lite_fp16:
+                option.enable_lite_fp16()
+        elif backend == "default":
+            return option
+        else:
+            raise Exception(
+                "While inference with CPU, only support default/lite now, {} is not supported.".
+                format(backend))                
    else:
        raise Exception(
-            "Only support device CPU/GPU now, {} is not supported.".format(
+            "Only support device CPU/GPU/Kunlunxin/Ascend now, {} is not supported.".format(
                device))

    return option
--- a/examples/vision/detection/paddledetection/README.md
+++ b/examples/vision/detection/paddledetection/README.md
@@ -19,8 +19,18 @@ Now FastDeploy supports the deployment of the following models
 - [SSD models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ssd)
 - [YOLOv5 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5)
 - [YOLOv6 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6)
- [YOLOv7 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)
+- [YOLOv7 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)  
+- [YOLOv8 models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov8)
 - [RTMDet models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet)
+- [RTMDet models](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet)
+- [CascadeRCNN models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/cascade_rcnn)
+- [PSSDet models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/rcnn_enhance)
+- [RetinaNet models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/retinanet)
+- [PPYOLOESOD models](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/smalldet)
+- [FCOS models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/fcos)
+- [TTFNet models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ttfnet)
+- [TOOD models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/tood)
+- [GFL models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/gfl)

 ## Export Deployment Model

@@ -58,7 +68,22 @@ The accuracy metric is from model descriptions in PaddleDetection. Refer to them
 | [yolov6_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6_l_300e_coco.tgz) | 229M | Box AP 51.0%|  |
 | [yolov6_s_400e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov6_s_400e_coco.tgz) | 68M | Box AP 43.4%|  |
 | [yolov7_l_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_l_300e_coco.tgz) | 145M | Box AP 51.0%|  |
-| [yolov7_x_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_x_300e_coco.tgz) | 277M | Box AP 53.0%|  |
+| [yolov7_x_300e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_x_300e_coco.tgz) | 277M | Box AP 53.0%|  |  
+| [cascade_rcnn_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/cascade_rcnn_r50_fpn_1x_coco.tgz) | 271M | Box AP 41.1%|  TensorRT、ORT not supported yet|
+| [cascade_rcnn_r50_vd_fpn_ssld_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.tgz) | 271M | Box AP 45.0%|  TensorRT、ORT not supported yet|
+| [faster_rcnn_enhance_3x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/faster_rcnn_enhance_3x_coco.tgz) | 119M | Box AP 41.5%|  TensorRT、ORT not supported yet|
+| [fcos_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/fcos_r50_fpn_1x_coco.tgz) | 129M | Box AP 39.6%|  TensorRT not supported yet |
+| [gfl_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/gfl_r50_fpn_1x_coco.tgz) | 128M | Box AP 41.0%|  TensorRT not supported yet|
+| [ppyoloe_crn_l_80e_sliced_visdrone_640_025](https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_80e_sliced_visdrone_640_025.tgz) | 200M | Box AP 31.9%|  |
+| [retinanet_r101_fpn_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r101_fpn_2x_coco.tgz) | 210M | Box AP 40.6%| TensorRT、ORT not supported yet|
+| [retinanet_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r50_fpn_1x_coco.tgz) | 136M | Box AP 37.5%| TensorRT、ORT not supported yet|
+| [tood_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/tood_r50_fpn_1x_coco.tgz) | 130M | Box AP 42.5%| TensorRT、ORT not supported yet|
+| [ttfnet_darknet53_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ttfnet_darknet53_1x_coco.tgz) | 178M | Box AP 33.5%| TensorRT、ORT not supported yet|  
+| [yolov8_x_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_x_500e_coco.tgz) | 265M | Box AP 53.8%
+| [yolov8_l_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_l_500e_coco.tgz) | 173M | Box AP 52.8%
+| [yolov8_m_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_m_500e_coco.tgz) | 99M | Box AP 50.2%
+| [yolov8_s_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_s_500e_coco.tgz) | 43M | Box AP 44.9%
+| [yolov8_n_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_n_500e_coco.tgz) | 13M | Box AP 37.3%

 ## Detailed Deployment Documents

--- a/examples/vision/detection/paddledetection/README_CN.md
+++ b/examples/vision/detection/paddledetection/README_CN.md
@@ -19,7 +19,8 @@
 - [SSD系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ssd)
 - [YOLOv5系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5)
 - [YOLOv6系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6)
- [YOLOv7系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)
+- [YOLOv7系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)  
+- [YOLOv8系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov8)
 - [RTMDet系列模型](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet)
 - [CascadeRCNN系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/cascade_rcnn)
 - [PSSDet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/rcnn_enhance)
@@ -78,7 +79,12 @@
 | [retinanet_r101_fpn_2x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r101_fpn_2x_coco.tgz) | 210M | Box AP 40.6%|  暂不支持TensorRT、ORT |
 | [retinanet_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/retinanet_r50_fpn_1x_coco.tgz) | 136M | Box AP 37.5%|  暂不支持TensorRT、ORT |
 | [tood_r50_fpn_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/tood_r50_fpn_1x_coco.tgz) | 130M | Box AP 42.5%|  暂不支持TensorRT、ORT |
-| [ttfnet_darknet53_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ttfnet_darknet53_1x_coco.tgz) | 178M | Box AP 33.5%|  暂不支持TensorRT、ORT |
+| [ttfnet_darknet53_1x_coco](https://bj.bcebos.com/paddlehub/fastdeploy/ttfnet_darknet53_1x_coco.tgz) | 178M | Box AP 33.5%|  暂不支持TensorRT、ORT |  
+| [yolov8_x_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_x_500e_coco.tgz) | 265M | Box AP 53.8%
+| [yolov8_l_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_l_500e_coco.tgz) | 173M | Box AP 52.8%
+| [yolov8_m_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_m_500e_coco.tgz) | 99M | Box AP 50.2%
+| [yolov8_s_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_s_500e_coco.tgz) | 43M | Box AP 44.9%
+| [yolov8_n_500e_coco](https://bj.bcebos.com/paddlehub/fastdeploy/yolov8_n_500e_coco.tgz) | 13M | Box AP 37.3%

 ## 详细部署文档

--- a/examples/vision/detection/paddledetection/python/infer_yolov8.py
+++ b/examples/vision/detection/paddledetection/python/infer_yolov8.py
@@ -32,6 +32,9 @@ def build_option(args):
    if args.device.lower() == "kunlunxin":
        option.use_kunlunxin()

+    if args.device.lower() == "ascend":
+        option.use_ascend()
+        
    if args.device.lower() == "gpu":
        option.use_gpu()

--- a/fastdeploy/vision/detection/ppdet/model.h
+++ b/fastdeploy/vision/detection/ppdet/model.h
@@ -256,6 +256,7 @@ class FASTDEPLOY_DECL PaddleYOLOv8 : public PPDetBase {
    valid_cpu_backends = {Backend::OPENVINO, Backend::ORT, Backend::PDINFER, Backend::LITE};
    valid_gpu_backends = {Backend::ORT, Backend::PDINFER, Backend::TRT};
    valid_kunlunxin_backends = {Backend::LITE};
+    valid_ascend_backends = {Backend::LITE};
    initialized = Initialize();
  }