Yoshiteru, K.

I think it's up to your VNC environment whether OpenGLES commands are correctly transferred to another PC or not, Isn't it ?

how about ```export DISPLAY=:0```

I've added a new config named "headless". Could you try below ? ``` (ssh to jetson with X forwarding) $ ssh -X [email protected] (On jetson) $ export DISPLAY=:10.0 $ cd...

hmmmm. I don't understand why gl2blazeface doesn't work although gl2classification work well. They are almost same implementation. Don't you have any OpenGL error logs ? ``` i am preferring to...

On current implementation, OpenGL is required in order to preprocess input images. (resize, crop, affine transform, color conversion (YUYA->RGB)). and unfortunately, current implementation requires showing window in order to use...

FYI. This is a screen capture of gl2blazeface forwarded to WindowsPC from Jetson nano. It works well. I used ```VcXsrv``` as a X Server. 

did you install libgles2-mesa-dev ? ``` sudo apt install libgles2-mesa-dev ```

I didn't generate any tflite models. In each directory of tflite, there is a README.md which describes where I downloaded the tflite file. for example, https://github.com/terryky/tflite_gles_app/blob/master/gl2age_gender/model/README.md https://github.com/terryky/tflite_gles_app/blob/master/gl2blazeface/blazeface_model/README.md

yes, I think it will works although I've never tested it on RK3399.

./tensorflow/bazel-bin/tensorflow/lite/libtensorflowlite.so could you read [README.md](https://github.com/terryky/tflite_gles_app#222-copy-tensorflow-lite-libraries-to-target-jetson--raspi)?