RunningLeon
commented
1 year ago @mozhijing hi, pls. dowload ort lib with cuda version. You could refer to this
Closed mozhijing closed 1 year ago
RunningLeon
commented
1 year ago @mozhijing hi, pls. dowload ort lib with cuda version. You could refer to this
mozhijing
commented
1 year ago @RunningLeon Thank you for your reply.I can't run on gpu, cpu is ok.Segmentation fault (core dumped) while running run on gpu: python3 pose_tracker.py cuda /data/rtmpose-ort/rtmdet-nano/ /data/rtmpose-ort/rtmpose-m/ /data/two-girls.mp4 --output /data/2/ [2023-06-02 03:05:28.905] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "/data/rtmpose-ort/rtmpose-m/" [2023-06-02 03:05:28.905] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "/data/rtmpose-ort/rtmdet-nano/" Segmentation fault (core dumped) run on cpu: python3 pose_tracker.py cpu /data/rtmpose-ort/rtmdet-nano/ /data/rtmpose-ort/rtmpose-m/ /data/two-girls.mp4 --output /data/2/ [2023-06-02 03:05:57.473] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "/data/rtmpose-ort/rtmpose-m/" [2023-06-02 03:05:57.473] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "/data/rtmpose-ort/rtmdet-nano/" [2023-06-02 03:05:57.533] [mmdeploy] [info] [inference.cpp:54] ["img"] <- ["data"] [2023-06-02 03:05:57.533] [mmdeploy] [info] [inference.cpp:65] ["post_output"] -> ["dets"] [2023-06-02 03:05:57.764] [mmdeploy] [info] [inference.cpp:54] ["img"] <- ["rois"] [2023-06-02 03:05:57.764] [mmdeploy] [info] [inference.cpp:65] ["post_output"] -> ["keypoints"]
RunningLeon
commented
1 year ago @irexyc hi, does postracker support ort+gpu?
irexyc
commented
1 year ago @mozhijing
Hi, how did you install mmdeploy_runtime ?
mozhijing
commented
1 year ago @irexyc Thank you for your reply.The onnxruntime-gpu version is inconsistent.There's no problem now
Checklist
Describe the bug
docker openmmlab/mmdeploy:ubuntu20.04-cuda11.3-mmdeploy1.1.0 log: [2023-06-01 08:56:33.505] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "/data/rtmpose-ort/rtmpose-m/" [2023-06-01 08:56:33.505] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "/data/rtmpose-ort/rtmdet-nano/" 2023-06-01 08:56:33.513433837 [E:onnxruntime:, provider_bridge_ort.cc:901 Ensure] Failed to load library libonnxruntime_providers_shared.so with error: libonnxruntime_providers_shared.so: cannot open shared object file: No such file or directory [2023-06-01 08:56:33.513] [mmdeploy] [error] [ort_net.cpp:205] unhandled exception when creating ORTNet: OrtSessionOptionsAppendExecutionProvider_Cuda: Failed to load shared library [2023-06-01 08:56:33.513] [mmdeploy] [error] [net_module.cpp:54] Failed to create Net backend: onnxruntime, config: { "context": { "device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": true,
"module": "Net",
"name": "rtmdet",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
[2023-06-01 08:56:33.513] [mmdeploy] [error] [task.cpp:99] error parsing config: {
"context": {
"device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": true,
"module": "Net",
"name": "rtmdet",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
[2023-06-01 08:56:33.513] [mmdeploy] [info] [inference.cpp:54] ["img"] <- ["data"]
[2023-06-01 08:56:33.513] [mmdeploy] [info] [inference.cpp:65] ["post_output"] -> ["dets"]
2023-06-01 08:56:33.533754882 [E:onnxruntime:, provider_bridge_ort.cc:901 Ensure] Failed to load library libonnxruntime_providers_shared.so with error: libonnxruntime_providers_shared.so: cannot open shared object file: No such file or directory
[2023-06-01 08:56:33.535] [mmdeploy] [error] [ort_net.cpp:205] unhandled exception when creating ORTNet: OrtSessionOptionsAppendExecutionProvider_Cuda: Failed to load shared library
[2023-06-01 08:56:33.535] [mmdeploy] [error] [net_module.cpp:54] Failed to create Net backend: onnxruntime, config: {
"context": {
"device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": false,
"module": "Net",
"name": "topdownposeestimator",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
[2023-06-01 08:56:33.535] [mmdeploy] [error] [task.cpp:99] error parsing config: {
"context": {
"device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": false,
"module": "Net",
"name": "topdownposeestimator",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
[2023-06-01 08:56:33.535] [mmdeploy] [info] [inference.cpp:54] ["img"] <- ["rois"]
[2023-06-01 08:56:33.535] [mmdeploy] [info] [inference.cpp:65] ["post_output"] -> ["keypoints"]
Segmentation fault (core dumped)
Reproduction
python3 pose_tracker.py cuda /data/rtmpose-ort/rtmdet-nano/ /data/rtmpose-ort/rtmpose-m/ /data/two-girls.mp4 --output_dir /data/output
Environment
Error traceback
No response