I am trying to train the GQN with shepard_metzler_5_parts dataset.
After the training has finished, I used the script mentioned in here to visualize the result. However, the generated image is just a black image.
So, the default training parameters is only for rooms_ring_camera? Do I need to change some of the training parameters in gqn_params.py for different dataset?
Hi @waiyc , please check out the latest update on the master branch. GQN now trains fine on all datasets and I have added jupyter notebooks for easier deployment of trained networks in prediction mode.
Hi,
I am trying to train the GQN with
shepard_metzler_5_parts
dataset. After the training has finished, I used the script mentioned in here to visualize the result. However, the generated image is just a black image.So, the default training parameters is only for
rooms_ring_camera
? Do I need to change some of the training parameters ingqn_params.py
for different dataset?