You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
pytorch-image-models/timm/models/layers
Ross Wightman 8bf63b6c6c
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
4 years ago
..
__init__.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
activations.py
activations_jit.py
activations_me.py
adaptive_avgmax_pool.py
blur_pool.py
bottleneck_attn.py
cbam.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
classifier.py
cond_conv2d.py
config.py
conv2d_same.py
conv_bn_act.py
create_act.py Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present. 4 years ago
create_attn.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
create_conv2d.py
create_norm_act.py
create_self_attn.py
drop.py
eca.py Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable. 4 years ago
evo_norm.py
gather_excite.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
global_context.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
halo_attn.py
helpers.py Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs. 4 years ago
inplace_abn.py
involution.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
lambda_layer.py
linear.py
median_pool.py
mixed_conv2d.py
mlp.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
norm.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
norm_act.py
padding.py
patch_embed.py
pool2d_same.py
selective_kernel.py
separable_conv.py
space_to_depth.py
split_attn.py
split_batchnorm.py
squeeze_excite.py Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy. 4 years ago
std_conv.py
swin_attn.py
test_time_pool.py
weight_init.py