-
由 Evan Shelhamer 提交于
This net is fine-tuned from VGG-16 all-at-once instead of in stages. All-at-once learning is faster and less tedious but gives an ever-so-slightly less accurate model.
44f93ec4
从无法访问的项目Fork
This net is fine-tuned from VGG-16 all-at-once instead of in stages. All-at-once learning is faster and less tedious but gives an ever-so-slightly less accurate model.