올라프의 AI 공부

논문 코드 1) ProbSparse self-attention parser.add_argument('--attn', type=str, default='prob', help='attention used in encoder, options:[prob, full]') 2) Self-attention distilling conv1d, maxpooling 사용하여 more focused feature map 형성 parser.add_argument('--distil', action='store_false', help='whether to use distilling in encoder, using this argument means not using distilling', default=True) 3) Genera..