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.

Ross Wightman 742c2d5247 Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.		3 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.	3 years ago
activations.py	…
activations_jit.py	…
activations_me.py	…
adaptive_avgmax_pool.py	…
blur_pool.py	Remove filter hack from BlurPool w/ non-persistent buffer. Use BlurPool2d instead of AntiAliasing.. for TResNet. Breaks PyTorch < 1.6.	4 years ago
bottleneck_attn.py	Improved (hopefully) init for SA/SA-like layers used in ByoaNets	4 years ago
cbam.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	3 years ago
classifier.py	…
cond_conv2d.py	…
config.py	…
conv2d_same.py	…
conv_bn_act.py	Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.	4 years ago
create_act.py	Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.	3 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.	3 years ago
create_conv2d.py	Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354.	4 years ago
create_norm_act.py	Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.	4 years ago
create_self_attn.py	Add initial RedNet model / Involution layer impl for testing	4 years ago
drop.py	…
eca.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	3 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.	3 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.	3 years ago
halo_attn.py	Improved (hopefully) init for SA/SA-like layers used in ByoaNets	4 years ago
helpers.py	EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.	4 years ago
inplace_abn.py	Update README, fix iabn pip version print.	4 years ago
involution.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	3 years ago
lambda_layer.py	Improved (hopefully) init for SA/SA-like layers used in ByoaNets	4 years ago
linear.py	…
median_pool.py	…
mixed_conv2d.py	Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354.	4 years ago
mlp.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	3 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.	3 years ago
norm_act.py	Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.	4 years ago
padding.py	…
patch_embed.py	Add levit, levit_c, and visformer model defs. Largely untested and not finished cleanup.	4 years ago
pool2d_same.py	…
selective_kernel.py	…
separable_conv.py	Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.	4 years ago
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.	3 years ago
std_conv.py	Add ECA-NFNet-L0 weights and update model name. Update README and bump version to 0.4.6	4 years ago
swin_attn.py	Improved (hopefully) init for SA/SA-like layers used in ByoaNets	4 years ago
test_time_pool.py	…
weight_init.py	Cleanup experimental vit weight init a bit	4 years ago