- 01 6月, 2021 5 次提交
-
-
由 Ross Wightman 提交于
Add Gather-Excite, Global Context, BAT, Non-Local attn modules and refactored all attn modules and factory for improved consistency. EfficientNet / MobileNetV3 backbones able to use a wider variety of attention modules.
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
-
- 31 5月, 2021 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
-
- 30 5月, 2021 1 次提交
-
-
由 Ross Wightman 提交于
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
-
- 29 5月, 2021 4 次提交
-
-
由 Ross Wightman 提交于
Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 28 5月, 2021 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
-
- 27 5月, 2021 1 次提交
-
-
由 Ross Wightman 提交于
Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
-
- 26 5月, 2021 9 次提交
-
-
由 Ross Wightman 提交于
LeVit, Visformer, RedNet/Involution models and layers
-
由 Ross Wightman 提交于
README: fix simple typos
-
由 Ross Wightman 提交于
-
由 Peter Vandenabeele 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 25 5月, 2021 3 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.
-
- 23 5月, 2021 2 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
- 22 5月, 2021 10 次提交
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
Merge branch 'master' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-master
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-
-
由 Ross Wightman 提交于
-
由 Ross Wightman 提交于
-