jun

how to train 2d106det？

1

if want train 2d106det,how to train 2d106det？

map_setx =int(forehead_x-map_setsize_w*(cos(radian_angele)/2+sin(radian_angele))) NameError: name 'forehead_x' is not define

ValueError: operands could not be broadcast together with shapes (12800,) (3200,)

4

ValueError: operands could not be broadcast together with shapes (12800,) (3200,)

什么时候更新模型上来？

2

关注很久了，一直在等更新模型

以openvino为后端运行ppocrv3cpu利用率低

1

以openvino为后端运行ppocrv3 cpu利用率低 命令： infer.py --det_model model/ch_PP-OCRv3_det_infer --cls_model model/ch_ppocr_mobile_v2.0_cls_infer --rec_model model/ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu --backend openvino [INFO] fastdeploy/backends/openvino/ov_backend.cc(161)::InitFromPaddle Compile OpenVINO model on device_name:CPU. [INFO] fastdeploy/runtime.cc(532)::Init Runtime initialized with...

在window的anconda环境下出现 no module named ‘resource’

1

在window的anconda环境下出现 no module named ‘resource’，请问如何解决？

疑问

1

问什么识别一张普通发票很多字段都识别不出来？是提示词有讲究

ppocrv4推理出错

1

mindtorch0.3_mindspore2.3.0_torchnpu2.2.0_cann8.0 File "/home/ma-user/anaconda3/envs/MindSpore/lib/python3.9/multiprocessing/process.py", line 118, in start assert not _current_process._config.get('daemon'), \ AssertionError: daemonic processes are not allowed to have children [ERROR] MINDOCR(1847:281473157416000,Process-1:34):2024-09-17-06:55:19.239.330 [src/parallel/framework/module_base.py:40] RecInferNode init failed: daemonic processes are not...