9 Commits

Author	SHA1	Message	Date
Phil Wang	df656fe7c7	complete learnable memory ViT, for efficient fine-tuning and potentially plays into continual learning	2022-03-31 09:51:12 -07:00
Phil Wang	4e6a42a0ca	correct need for post-attention dropout	2022-03-30 10:50:57 -07:00
Yonghye Kwon	24ac8350bf	remove unused package	2021-08-30 18:25:03 +09:00
Yonghye Kwon	ca3cef9de0	Cleanup Attention Class	2021-08-30 18:05:16 +09:00
Yonghye Kwon	946815164a	Remove unused package	2021-08-20 13:44:57 +09:00
Phil Wang	6549522629	be able to accept non-square patches, thanks to @FilipAndersson245	2021-05-01 20:04:41 -07:00
Phil Wang	8135d70e4e	use hooks to retrieve attention maps for user without modifying ViT	2021-03-29 15:10:12 -07:00
Phil Wang	3067155cea	add recorder class, for recording attention across layers, for researchers	2021-03-29 11:08:19 -07:00
Phil Wang	15294c304e	remove masking, as it complicates with little benefit	2021-03-23 12:18:47 -07:00