Engine != nullptr,构建engine失败

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Loading weights: …/yolov5s.wts
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer* 173) [Convolution]: kernel weights has count 40320 but 6144 was expected
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer* 173) [Convolution]: count of 40320 weights in kernel, but kernel dimensions (1,1) with 128 input channels, 48 output channels and 1 groups were specified. Expected Weights count is 128 * 11 * 48 / 1 = 6144
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer 173) [Convolution]: kernel weights has count 40320 but 6144 was expected
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer* 173) [Convolution]: count of 40320 weights in kernel, but kernel dimensions (1,1) with 128 input channels, 48 output channels and 1 groups were specified. Expected Weights count is 128 * 11 * 48 / 1 = 6144
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer 173) [Convolution]: kernel weights has count 40320 but 6144 was expected
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer* 173) [Convolution]: count of 40320 weights in kernel, but kernel dimensions (1,1) with 128 input channels, 48 output channels and 1 groups were specified. Expected Weights count is 128 * 11 * 48 / 1 = 6144
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer 173) [Convolution]: kernel weights has count 40320 but 6144 was expected
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer* 173) [Convolution]: count of 40320 weights in kernel, but kernel dimensions (1,1) with 128 input channels, 48 output channels and 1 groups were specified. Expected Weights count is 128 * 11 * 48 / 1 = 6144
Building engine, please wait for a while…
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer 173) [Convolution]: kernel weights has count 40320 but 6144 was expected
[07/04/2024-08:47:32] [E] [TRT] (Unnamed Layer* 173) [Convolution]: count of 40320 weights in kernel, but kernel dimensions (1,1) with 128 input channels, 48 output channels and 1 groups were specified. Expected Weights count is 128 * 11 * 48 / 1 = 6144
[07/04/2024-08:47:32] [E] [TRT] Could not compute dimensions for (Unnamed Layer 173) [Convolution]_output, because the network is not valid.
[07/04/2024-08:47:32] [E] [TRT] Network validation failed.
Build engine successfully!
yolov5: /home/deepstreamtest/deepstream-5.1CRT/sources/deepstream_yolo/Yolov5-in-Deepstream-5.0/yolov5.cpp:440: void APIToModel(unsigned int, nvinfer1::IHostMemory**): Assertion `engine != nullptr’ failed.
Aborted

2

hi @13730054723 ,
Can you share with us the onnx model and repro steps?

Thanks