Day 25
The three models were done training by this morning, and I tested all of them- they were ok, but the paired dataset ones still have splotches on them. Some of the generator losses were actually increasing after a certain number of epochs (around 11-12) so I decided to train another one with the paired dataset for 12 epochs. I’m also retraining the best unpaired one I have so far and also the paired version for the original model because I still don’t have the RGB to thermal images. However I might end up having to retrain them because I might have messed up the saved files again. There are so many of them!
I also think that some of the issues might be due to overfitting so I added more dropouts to the model and starting running that too. I can train four right now because I managed to get one of them onto Grissom. Eventually I'm going to change more of the hyperparameters, and I'm also thinking of optimizing the generator more often. I can always run more at home and get the graphs from today on Monday.
At 12:04 pm the computer taskbar froze and so did the main screen, however all the applications are still working (I just can’t open new ones). It’s a little inconvenient but not a major issue. I ran some tests during training to see how they're doing- the unpaired ones are decent again, but the paired ones are getting worse? I'll keep checking in on them. I also worked on adding pictures to my presentation- it’s not entirely organized but I think I can make it work.
As for non-coding activities, I ate my lunch in about 5 minutes and then spent the rest of the time walking around campus. I went down the Quarter Mile toward housing- the incoming freshmen might be moving in right now because there were a lot of people there. I went by the nature trails and then Eastman Quad on the way back. In the afternoon I also visited the Remote Sensing Lab and watched Jocelyn and Hannah work on their wet sieving.
Ahh only one week left!
I also think that some of the issues might be due to overfitting so I added more dropouts to the model and starting running that too. I can train four right now because I managed to get one of them onto Grissom. Eventually I'm going to change more of the hyperparameters, and I'm also thinking of optimizing the generator more often. I can always run more at home and get the graphs from today on Monday.
At 12:04 pm the computer taskbar froze and so did the main screen, however all the applications are still working (I just can’t open new ones). It’s a little inconvenient but not a major issue. I ran some tests during training to see how they're doing- the unpaired ones are decent again, but the paired ones are getting worse? I'll keep checking in on them. I also worked on adding pictures to my presentation- it’s not entirely organized but I think I can make it work.
As for non-coding activities, I ate my lunch in about 5 minutes and then spent the rest of the time walking around campus. I went down the Quarter Mile toward housing- the incoming freshmen might be moving in right now because there were a lot of people there. I went by the nature trails and then Eastman Quad on the way back. In the afternoon I also visited the Remote Sensing Lab and watched Jocelyn and Hannah work on their wet sieving.
Ahh only one week left!
Comments
Post a Comment