Where is the inference part? (推理部分在哪里?)

[SwEngine]

Where is the inference.cu? I run the code and the outputs are like below. When I look to output images, there are no bounding boxes, it does not do inference. So I though that you did not completed the inference part. If you completed, can you share?

/content/yolov7-face-tensorrt
mkdir: cannot create directory ‘build’: File exists
/content/yolov7-face-tensorrt/build
-- Configuring done
-- Generating done
-- Build files have been written to: /content/yolov7-face-tensorrt/build
[ 14%] Building CXX object CMakeFiles/yolov7_face.dir/yolov7-face.cpp.o
[ 28%] Linking CXX executable yolov7_face
[ 71%] Built target yolov7_face
[100%] Built target onnx2trt
/root
/

/content/yolov7-face-tensorrt
/content/yolov7-face-tensorrt/build
[05/10/2023-10:01:31] [W] [TRT] CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage and speed up TensorRT initialization. See "Lazy Loading" section of CUDA documentation https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#lazy-loading
[05/10/2023-10:01:31] [W] [TRT] onnx2trt_utils.cpp:374: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[05/10/2023-10:01:31] [W] [TRT] onnx2trt_utils.cpp:400: One or more weights outside the range of INT32 was clamped
[05/10/2023-10:11:39] [W] [TRT] TensorRT encountered issues when converting weights between types and that could affect accuracy.
[05/10/2023-10:11:39] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
[05/10/2023-10:11:39] [W] [TRT] Check verbose logs for the list of affected weights.
[05/10/2023-10:11:39] [W] [TRT] - 76 weights are affected by this issue: Detected subnormal FP16 values.
convert seccuss!
/content/yolov7-face-tensorrt
/content

/content/yolov7-face-tensorrt
/content/yolov7-face-tensorrt/build
[05/10/2023-10:33:32] [W] [TRT] CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage and speed up TensorRT initialization. See "Lazy Loading" section of CUDA documentation https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#lazy-loading
../images/22_Picnic_Picnic_22_290.jpg   time_gap: 6.8426ms 
../images/22_Picnic_Picnic_22_152.jpg   time_gap: 6.5877ms 
../images/22_Picnic_Picnic_22_140.jpg   time_gap: 6.52203ms 
../images/22_Picnic_Picnic_22_208.jpg   time_gap: 6.57545ms 
../images/test.jpg   time_gap: 7.97395ms 
../images/22_Picnic_Picnic_22_308.jpg   time_gap: 6.65615ms 
../images/22_Picnic_Picnic_22_241.jpg   time_gap: 6.53058ms 
../images/22_Picnic_Picnic_22_10.jpg   time_gap: 6.50339ms 
../images/22_Picnic_Picnic_22_36.jpg   time_gap: 6.5744ms 
../images/22_Picnic_Picnic_22_928.jpg   time_gap: 6.5951ms 
averageTime:6.72431ms
/content/yolov7-face-tensorrt
/content