ppyoloe导出预训练模型，进行推理时报错

[atczyh]

问题确认 Search before asking

• 我已经查询历史issue，没有发现相似的bug。I have searched the issues and found no similar bug report.

Bug组件 Bug Component

Deploy

Bug描述 Describe the Bug

参考官方案例导出预训练模型，python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://bj.bcebos.com/v1/paddledet/models/pretrained/ppyoloe_crn_x_obj365_pretrained.pdparams exclude_nms=True
使用命令进行推理
python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --run_mode=paddle --device=cpu
报错
----------- Model Configuration -----------
Model Arch: YOLO
Transform Order:
--transform op: Resize
--transform op: NormalizeImage
--transform op: Permute
Found 13 inference images in total.
detector.predict_image
Traceback (most recent call last):
File "deploy/python/infer.py", line 1229, in
main()
File "deploy/python/infer.py", line 1197, in main
detector.predict_image(
File "deploy/python/infer.py", line 416, in predict_image
visualize(
File "deploy/python/infer.py", line 1112, in visualize
im_results['boxes'] = result['boxes'][start_idx:start_idx +
TypeError: only integer scalar arrays can be converted to a scalar index

复现环境 Environment

windows
paddle 2.3.2
paddledetection release 2.7
cpu推理

Bug描述确认 Bug description confirmation

• 我确认已经提供了Bug复现步骤、代码改动说明、以及环境信息，确认问题是可以复现的。I confirm that the bug replication steps, code change instructions, and environment information have been provided, and the problem can be reproduced.

是否愿意提交PR？ Are you willing to submit a PR?

• 我愿意提交PR！I'd like to help by submitting a PR!

[lyuwenyu]

你把exclude_nms=True 去掉导出->infer再试一下

[atczyh]

E:\PaddleDetection>python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --run_mode=paddle --device=gpu
----------- Running Arguments -----------
action_file: None
batch_size: 1
camera_id: -1
collect_trt_shape_info: False
combine_method: nms
cpu_threads: 1
device: gpu
enable_mkldnn: False
enable_mkldnn_bfloat16: False
image_dir: demo/
image_file: None
match_metric: ios
match_threshold: 0.6
model_dir: output_inference/ppyoloe_plus_crn_l_80e_coco
output_dir: output
overlap_ratio: [0.25, 0.25]
random_pad: False
reid_batch_size: 50
reid_model_dir: None
run_benchmark: False
run_mode: paddle
save_images: True
save_mot_txt_per_img: False
save_mot_txts: False
save_results: False
scaled: False
slice_infer: False
slice_size: [640, 640]
threshold: 0.5
tracker_config: None
trt_calib_mode: False
trt_max_shape: 1280
trt_min_shape: 1
trt_opt_shape: 640
tuned_trt_shape_file: shape_range_info.pbtxt
use_coco_category: False
use_dark: True
use_fd_format: False
use_gpu: False
video_file: None
window_size: 50

FLAGS Namespace(action_file=None, batch_size=1, camera_id=-1, collect_trt_shape_info=False, combine_method='nms', cpu_threads=1, device='GPU', enable_mkldnn=False, enable_mkldnn_bfloat16=False, image_dir='demo/', image_file=None, match_metric='ios', match_threshold=0.6, model_dir='output_inference/ppyoloe_plus_crn_l_80e_coco', output_dir='output', overlap_ratio=[0.25, 0.25], random_pad=False, reid_batch_size=50, reid_model_dir=None, run_benchmark=False, run_mode='paddle', save_images=True, save_mot_txt_per_img=False, save_mot_txts=False, save_results=False, scaled=False, slice_infer=False, slice_size=[640, 640], threshold=0.5, tracker_config=None, trt_calib_mode=False, trt_max_shape=1280, trt_min_shape=1, trt_opt_shape=640, tuned_trt_shape_file='shape_range_info.pbtxt', use_coco_category=False, use_dark=True, use_fd_format=False, use_gpu=False, video_file=None, window_size=50)
----------- Model Configuration -----------
Model Arch: YOLO
Transform Order:
--transform op: Resize
--transform op: NormalizeImage
--transform op: Permute

Found 13 inference images in total.
detector.predict_image
save result to: output\orange_71.jpg
Test iter 0
save result to: output\road554.png
Test iter 1
save result to: output\000000014439_640x640.jpg
Test iter 2
save result to: output\P0072__1.0__0___0.png
Test iter 3
save result to: output\000000570688.jpg
Test iter 4
save result to: output\visdrone_0000315_01601_d_0000509.jpg
Test iter 5
save result to: output\000000087038.jpg
Test iter 6
save result to: output\lane00000.jpg
Test iter 7
save result to: output\P0861__1.0__1154___824.png
Test iter 8
save result to: output\39006.jpg
Test iter 9
save result to: output\000000014439.jpg
Test iter 10
save result to: output\car.jpg
Test iter 11
save result to: output\hrnet_demo.jpg
Test iter 12
------------------ Inference Time Info ----------------------
total_time(ms): 1769.9, img_num: 13
average latency time(ms): 136.15, QPS: 7.345048
preprocess_time(ms): 35.40, inference_time(ms): 100.80, postprocess_time(ms): 0.00

去掉之后没报错了，但是没法正常输出推理结果。demo里的图识别之后没有框

[lyuwenyu]

确定参数加载了？