search

nwesem / mtcnn_facenet_cpp_tensorRT

Face Recognition on NVIDIA Jetson (Nano) using TensorRT
GNU General Public License v3.0
200 stars 72 forks source link

Failed to parse UFF #7

Open swetha-sree opened 4 years ago

swetha-sree commented 4 years ago

ERROR: UffParser: Unsupported number of graph 0 Failed to parse UFF terminate called after throwing an instance of 'std::exception' what(): std::exception Aborted (core dumped)

Hi above is the stack trace for the error while executing ./mtcnn_facenet_cpp_tensorRT Hardware: Jetson Nano with Jetpack 4.2.1 Tensorflow Version: Tried both 1.14 and 1.15 TensorRT: 5.1.6.1

PhilipCNel commented 4 years ago

@swetha-sree did you remember to move the FaceNet.uff to the FaceNet models folder?

luanphamng commented 4 years ago

I tried tensorRT 1.15 and it working great. Please follow Nvidia guidelines for install tensorRT here: Installation guide - [](https://docs.nvidia.com/deeplearning/frameworks/install-tf-jetson-platform/index.html 5 )

mel0615 commented 4 years ago

Hi I had the same error while executing mtcnn_facenet_cpp_tensorRT. Finally I found that I compiled the project under the root directory but not build dir, so that the build files and executable file were in the root dir. Please check the path. Hope it helps. TF: 1.14 TRT: 5.1.5.0

nwesem commented 3 years ago

Try new release jp4.4 with Jetpack 4.4 and tensorflow 1.15 and let me know if that helped. Thanks