15 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Cian-H	4212c543f8	Update before first push to remote	2024-05-15 16:38:40 +01:00
Cian-H	15a57cc229	Added wandb logging	2024-05-15 16:37:53 +01:00
Cian-H	6600a79f71	Added more varied semantic loss functions	2024-05-15 16:37:53 +01:00
Cian-H	01127de4b3	Added testing step at end of training	2024-05-15 16:37:53 +01:00
Cian-H	62649a39da	Modified model to use SGD for less optimal training ... There's no point having a loss function testing sandbox where the baseling trains perfectly in 2 epochs. I've DEoptimised the training in this commit to ensure the testing sandbox is actually useful.	2024-05-15 16:37:53 +01:00
Cian-H	389c47ef28	Fixed similarity matrix normalization	2024-05-15 16:37:53 +01:00
Cian-H	66b23a8e76	Minimized model and prepared for testing new loss functions	2024-05-15 16:37:53 +01:00
Cian Hughes	708f9952b3	First functional training loop	2024-05-15 16:37:53 +01:00
Cian-H	674175b260	Added trainer and made dataset hot-swappable	2024-05-15 16:37:53 +01:00
Cian-H	63bea4d355	Updated dataloader to default to tensor transform	2024-05-15 16:37:53 +01:00
Cian-H	02d70964e1	Added image transformations to dataset fetching	2024-05-15 16:37:53 +01:00
Cian-H	223b064564	Tweaked dataloader for more reliable loading	2024-05-13 15:38:50 +01:00
Cian Hughes	8204109561	Created consistent dataloader	2024-05-13 15:29:55 +01:00
Cian Hughes	6df0fea652	Modifications to env	2024-05-13 14:59:27 +01:00
Cian Hughes	0782af696b	Initial env configuration	2024-05-13 11:41:35 +01:00