mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-12 20:11:20 +08:00
8d357814e8
* update * update * Update infer_ppyoloe_demo.cc --------- Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
69 lines
1.8 KiB
Python
Executable File
69 lines
1.8 KiB
Python
Executable File
import cv2
|
||
import os
|
||
import fastdeploy as fd
|
||
|
||
|
||
def parse_arguments():
|
||
import argparse
|
||
import ast
|
||
parser = argparse.ArgumentParser()
|
||
parser.add_argument(
|
||
"--model_dir",
|
||
default=None,
|
||
help="Path of PaddleDetection model directory")
|
||
parser.add_argument(
|
||
"--image", default=None, help="Path of test image file.")
|
||
parser.add_argument(
|
||
"--device",
|
||
type=str,
|
||
default='cpu',
|
||
help="Type of inference device, support 'kunlunxin', 'cpu' or 'gpu'.")
|
||
parser.add_argument(
|
||
"--use_trt",
|
||
type=ast.literal_eval,
|
||
default=False,
|
||
help="Wether to use tensorrt.")
|
||
return parser.parse_args()
|
||
|
||
|
||
def build_option(args):
|
||
option = fd.RuntimeOption()
|
||
option.use_cpu()
|
||
option.use_tvm_backend()
|
||
return option
|
||
|
||
|
||
args = parse_arguments()
|
||
|
||
if args.model_dir is None:
|
||
model_dir = fd.download_model(name='ppyoloe_crn_l_300e_coco')
|
||
else:
|
||
model_dir = args.model_dir
|
||
|
||
model_file = os.path.join(model_dir, "tvm_model.so")
|
||
params_file = os.path.join(model_dir, "tvm_model.params")
|
||
config_file = os.path.join(model_dir, "infer_cfg.yml")
|
||
|
||
# 配置runtime，加载模型
|
||
runtime_option = build_option(args)
|
||
model = fd.vision.detection.PPYOLOE(
|
||
model_file,
|
||
params_file,
|
||
config_file,
|
||
runtime_option=runtime_option,
|
||
model_format=fd.ModelFormat.TVMFormat)
|
||
model.postprocessor.apply_nms()
|
||
# 预测图片检测结果
|
||
if args.image is None:
|
||
image = fd.utils.get_detection_test_image()
|
||
else:
|
||
image = args.image
|
||
im = cv2.imread(image)
|
||
result = model.predict(im)
|
||
print(result)
|
||
|
||
# 预测结果可视化
|
||
vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5)
|
||
cv2.imwrite("visualized_result.jpg", vis_im)
|
||
print("Visualized result save in ./visualized_result.jpg")
|