Yolov7 performance bad - 10 FPS only on Orin AGX 64 GB #61
Description
I followed the Yolov7 tutorial here.
Exported the onnx from the official pt file. Adjusted the paths in the config files. It successfully built the engine, but I'm getting 10 FPS only (compared to the promised >100).
Here is the output after conversion:
WARNING: [TRT]: If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
WARNING: [TRT]: Check verbose logs for the list of affected weights.
WARNING: [TRT]: - 82 weights are affected by this issue: Detected subnormal FP16 values.
WARNING: [TRT]: - 2 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
0:40:28.444976296 26592 0xaaaad0efc090 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1955> [UID = 1]: serialize cuda engine to file: /home/nvidia/Documents/yolo_deepstream/deepstream_yolo/yolov7.onnx_b16_gpu0_fp16.engine successfully
INFO: [FullDims Engine Info]: layers num: 2
0 INPUT kFLOAT images 3x640x640 min: 1x3x640x640 opt: 16x3x640x640 Max: 16x3x640x640
1 OUTPUT kFLOAT output 25200x85 min: 0 opt: 0 Max: 0
...
**PERF: 9.78 (9.76) 9.62 (9.60) 9.63 (9.61) 9.78 (9.76) 9.64 (9.62) 9.62 (9.60) 9.63 (9.61) 9.63 (9.61) 9.78 (9.76) 9.63 (9.61) 9.78 (9.76) 10.20 (10.17) 9.78 (9.76) 9.63 (9.61) 9.78 (9.76) 9.78 (9.76)
**PERF: 10.11 (9.89) 10.11 (9.81) 10.11 (9.81) 10.11 (9.89) 10.11 (9.82) 10.11 (9.81) 10.11 (9.81) 10.11 (9.81) 10.11 (9.89) 10.11 (9.81) 10.11 (9.89) 10.11 (10.08) 10.11 (9.89) 10.11 (9.81) 10.11 (9.89) 10.11 (9.89)
**PERF: 10.11 (10.00) 10.11 (9.95
Have I exported the onnx incorrecly or might I have missed sth.?