jenspetersen / gqn-pytorch Goto Github PK

Hi,

Many thanks for your contribution on implementing GQN.

Recently, I implemented GQN. After the training on rooms_ring_camera, I found that the loss will converge to around 6950 after 200K iterations, which means after the sigma decrease to 0.7, the loss will maintain at a stable level. But in their original paper, the final loss is just 6.1. I don’t understand the where is the problem. Do you have the same problem? Many thanks in advance!

Looking forward to your reply!

Dear jenspetersen,

I checked the gqn dataset from https://github.com/deepmind/gqn-datasets. Shepard_metzler_7_parts contains 900 tfrecords for training. Each tfrecord has 20 scenes. So there are only 18000 scenes. For Mazes, there are 1080 records with 100 scenes for each record, which means 108000 in total.

So I think this link just contains a part of the whole data, right? If so, could you send the link for the whole dataset? Many thanks ion advance!

Best,
Bing

Thanks for your code ! Can you upload your trained model also. I would like to help to create the test function.