when trying to test the model on a video or through the cam i get these errors
[TRT] INVALID_ARGUMENT: Cannot find binding of given name: data
[TRT] failed to find requested input layer data in network
[TRT] device GPU, failed to create resources for CUDA engine
[TRT] failed to create TensorRT engine for models/tt/ssd-mobilenet.onnx, device GPU
[TRT] detectNet – failed to initialize.
detectnet: failed to load detectNet model
Hi @BLACK_CAT, it looks like the --input-blob=input_0 --output-cvg=scores --output-bbox=boxes part of your command line got cut off and wasn’t executed. Make sure that part is included in the command you run.
turns out you are right, for some reason when i put the command it appears full but the part that get executed is missing the --input part and i had to type it manually. BUT still the test works on pictures but not videos or CSI cam.
the camera works when i try camera-capture csi://0
What’s the command line you are running for camera? Is it similar to this?
detectnet --model=models/fruit/ssd-mobilenet.onnx --labels=models/fruit/labels.txt --input-blob=input_0 --output-cvg=scores --output-bbox=boxes csi://0
yes its exactly like this.
alright i was able to solve it by installing OpenCV throu sudo apt-get install
python3-opencv