Hello, I’m trying to inference yolov3 onnx.
I’ve created a /yolo directory in /networks of jetson-inference from (GitHub - dusty-nv/jetson-inference: Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.)
and I run the following command:
./detectnet-console dog_0.jpg output_0.jpg --model=$NET/yolov3.onnx --input_blob=data --output_cvg=coverage --output_bbox=bboxes --class_labels=$NET/labels.txt
I got the following error:
detectNet – loading detection network model from:
– prototxt NULL
– model networks/yolo/yolov3.onnx
– input_blob ‘data’
– output_cvg ‘coverage’
– output_bbox ‘bboxes’
– mean_pixel 0.000000
– mean_binary NULL
– class_labels networks/yolo/labels.txt
– threshold 0.500000
– batch_size 1
[TRT] TensorRT version 5.0.6
[TRT] loading NVIDIA plugins…
[TRT] completed loading NVIDIA plugins.
[TRT] detected model format - ONNX (extension ‘.onnx’)
[TRT] desired precision specified for GPU: FASTEST
[TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT] native precisions detected for GPU: FP32, FP16, INT8
[TRT] selecting fastest native precision for GPU: FP16
[TRT] attempting to open engine cache file networks/yolo/yolov3.onnx.1.1.GPU.FP16.engine
[TRT] cache file not found, profiling network model on device GPU
[TRT] device GPU, loading /home/flash/jetson-inference/build/aarch64/bin/ networks/yolo/yolov3.onnx
Input filename: networks/yolo/yolov3.onnx
ONNX IR version: 0.0.5
Opset version: 10
Producer name: keras2onnx
Producer version: 1.5.1
Domain: onnx
Model version: 0
Doc string:
WARNING: ONNX model has a newer ir_version (0.0.5) than this parser was built against (0.0.3).
[TRT] Parameter check failed at: …/builder/Network.cpp::addInput::406, condition: isValidDims(dims)
ERROR: /home/erisuser/p4sw/sw/gpgpu/MachineLearning/DIT/release/5.0/parsers/onnxOpenSource/ModelImporter.cpp:82 In function importInput:
[8] Assertion failed: *tensor = importer_ctx->network()->addInput( input.name().c_str(), trt_dtype, trt_dims)
[TRT] failed to parse ONNX model ‘networks/yolo/yolov3.onnx’
[TRT] device GPU, failed to load networks/yolo/yolov3.onnx
detectNet – failed to initialize.
detectnet-console: failed to initialize detectNet