[Lite] Support PaddleYOLOv8 with Lite Backend (PaddlePaddle#1145)

* [Model] Support PaddleYOLOv8 model * [YOLOv8] Add PaddleYOLOv8 pybind * [Other] update from latest develop (#30) * [Backend] Remove all lite options in RuntimeOption (PaddlePaddle#1109) * Remove all lite options in RuntimeOption * Fix code error * move pybind * Fix build error * [Backend] Add TensorRT FP16 support for AdaptivePool2d (PaddlePaddle#1116) * add fp16 cuda kernel * fix code bug * update code * [Doc] Fix KunlunXin doc (PaddlePaddle#1139) fix kunlunxin doc * [Model] Support PaddleYOLOv8 model (PaddlePaddle#1136) Co-authored-by: Jason <[email protected]> Co-authored-by: yeliang2258 <[email protected]> * [YOLOv8] add PaddleYOLOv8 pybind11 (PaddlePaddle#1144) (#31) * [Model] Support PaddleYOLOv8 model * [YOLOv8] Add PaddleYOLOv8 pybind * [Other] update from latest develop (#30) * [Backend] Remove all lite options in RuntimeOption (PaddlePaddle#1109) * Remove all lite options in RuntimeOption * Fix code error * move pybind * Fix build error * [Backend] Add TensorRT FP16 support for AdaptivePool2d (PaddlePaddle#1116) * add fp16 cuda kernel * fix code bug * update code * [Doc] Fix KunlunXin doc (PaddlePaddle#1139) fix kunlunxin doc * [Model] Support PaddleYOLOv8 model (PaddlePaddle#1136) Co-authored-by: Jason <[email protected]> Co-authored-by: yeliang2258 <[email protected]> Co-authored-by: Jason <[email protected]> Co-authored-by: yeliang2258 <[email protected]> Co-authored-by: Jason <[email protected]> Co-authored-by: yeliang2258 <[email protected]> * [benchmark] add PaddleYOLOv8 -> benchmark * [benchmark] add PaddleYOLOv8 -> benchmark * [Lite] Support PaddleYOLOv8 with Lite Backend Co-authored-by: Jason <[email protected]> Co-authored-by: yeliang2258 <[email protected]>
DefTruth · Jan 14, 2023 · f969967 · f969967
1 parent c797d31
commit f969967
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 3 deletions.
diff --git a/benchmark/benchmark_ppdet.py b/benchmark/benchmark_ppdet.py
@@ -17,7 +17,7 @@
 import os
 import numpy as np
 import time
-
+from tqdm import tqdm
 
 def parse_arguments():
     import argparse
@@ -263,6 +263,9 @@ def cpu_stat_func(self, q, pid, interval=0.0):
         elif "yolov3" in args.model:
             model = fd.vision.detection.YOLOv3(
                 model_file, params_file, config_file, runtime_option=option)
+        elif "yolov8" in args.model:
+            model = fd.vision.detection.PaddleYOLOv8(
+                model_file, params_file, config_file, runtime_option=option)
         elif "ppyolo_r50vd_dcn_1x_coco" in args.model or "ppyolov2_r101vd_dcn_365e_coco" in args.model:
             model = fd.vision.detection.PPYOLO(
                 model_file, params_file, config_file, runtime_option=option)
@@ -284,7 +287,7 @@ def cpu_stat_func(self, q, pid, interval=0.0):
 
         model.enable_record_time_of_runtime()
         im_ori = cv2.imread(args.image)
-        for i in range(args.iter_num):
+        for i in tqdm(range(args.iter_num)):
             im = im_ori
             start = time.time()
             result = model.predict(im)

diff --git a/fastdeploy/vision/detection/ppdet/model.h b/fastdeploy/vision/detection/ppdet/model.h
@@ -253,7 +253,7 @@ class FASTDEPLOY_DECL PaddleYOLOv8 : public PPDetBase {
                const ModelFormat& model_format = ModelFormat::PADDLE)
       : PPDetBase(model_file, params_file, config_file, custom_option,
                   model_format) {
-    valid_cpu_backends = {Backend::OPENVINO, Backend::ORT, Backend::PDINFER};
+    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};
     initialized = Initialize();