Santosh Shriyan

I am able to test the image but only with comparison mode, basically where the BiCu, ESRGAN, HR outputs are stitched. I am not able to get a singular up-scaled...

I followed the mentioned commands in readme.md I get the following error: ` bash ./test.sh BD TecoGAN 2021-06-24 12:44:09,507 [INFO]: ======================================== 2021-06-24 12:44:09,507 [INFO]: Testing model: TecoGAN_BD_iter500000 2021-06-24 12:44:09,507 [INFO]:...

Is an update from TF=1.8.0-gpu-py3 to 1.15.0-gpu-py3 in the pipeline

2

The reason for this request is that newer hardware like the rtx30 series do not support cuda10.1 for TF=1.8.0. I have managed to train a model on 1.15.0-gpu-py3 docker image...

Not able to use in inference mode for higher resolution input.

1

I am trying to use it in inference mode for input resolution of 1920*1080 pixels image frames (runGan.py 1). I am using an nvidia 1060 6GB GPU and getting this...

I have managed to train the model using my own dataset with tensorflow-gpu:1.15.0 docker image. But when I tried to use that trained model for inference I got the following...

I have a multi-gpu system that I want to use for inference. I have changed all the cuda id to correspond to a available gpu. ``` i.e with tf.device('/gpu:0'): ---->...