Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) gpu t 4 • DeepStream Version 7 • JetPack Version (valid for Jetson only) • TensorRT Version latest deepstream dependency (i think 8.6) • NVIDIA GPU Driver Version (valid for GPU only) 353 • Issue Type( questions, new requirements, bugs) question • How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Hi
I wanna convert etlt file(FaceDetect from catalogs) to engine file but there is a problem!!
Tao-converter is deprecated from tao version 5.x!!! I search for new method a lot of time but i didn’t find anything! How can i do this?
This link is also deprecated https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/resources/tao-converter
You can still use the tao-converter to convert this FaceDetect model.
Please download it via wget --content-disposition 'https://api.ngc.nvidia.com/v2/resources/org/nvidia/team/tao/tao-converter/v5.1.0_8.6.3.1_x86/files?redirect=true&path=tao-converter' -O tao-converter to your T4.
Thanks🙏it’s work very well!
But for the sake of finetunning facedetect model how can i do it with tao version5.x because it’s not in the tao model list and also there is no facedetect in tao(5.x) notebook sample
I think your answer is wrong because there are a lot of trainable file like trainable_v1.0 in the file browser section
Pls help me to know how can i train it with this tlt file?
The trainable tlt file is in FaceDetect | NVIDIA NGC.
You can train with it. Again, Facedetect model is actually trained by detectnet_v2 network. You can use detectnet_v2 network.
You can also find this info in FaceDetect | NVIDIA NGC.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks