模型导出后进行预测，报MemoryError: std::bad_alloc的错误

[mayun123]

问题确认 Search before asking

• 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

执行命令python deploy/python/infer.py --model_dir=infer_model/rtdetr_r50vd_6x_coco_water --image_file=test_img/img/300874.jpg --device=GPU

结果报错，显示如下
----------- 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: None
image_file: test_img/img/300874.jpg
match_metric: ios
match_threshold: 0.6
model_dir: infer_model/rtdetr_r50vd_6x_coco_water
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]
task_type: Detection
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: DETR
Transform Order:
--transform op: Resize
--transform op: NormalizeImage
--transform op: Permute

Traceback (most recent call last):
File "deploy/python/infer.py", line 1266, in
main()
File "deploy/python/infer.py", line 1199, in main
detector = eval(detector_func)(
File "deploy/python/infer.py", line 108, in init
self.predictor, self.config = load_predictor(
File "deploy/python/infer.py", line 1098, in load_predictor
predictor = create_predictor(config)
MemoryError: std::bad_alloc

[mayun123]

换了一个模型yolov3_darknet53_270e_coco，报同样的错MemoryError: std::bad_alloc，执行命令
python deploy/python/infer.py --model_dir=./inference_model/yolov3_darknet53_270e_coco --image_file=./demo/000000014439.jpg --device=CPU

paddle版本3.0.0b1，paddledetection版本2.7

[mayun123]

换了3个不同的paddle版本2.6.2和3.0.0b1以及3.0.0b2，re-detr模型都不行

[leo-q8]

试试更早版本的的paddle吧