pytorch-image-models/timm/layers
Bill Psomas f393439d2c
Merge 82f75f4cbb into c8c4f256b8
2025-04-23 22:33:03 +03:00
..
__init__.py Wrap torch checkpoint() fn to default use_reentrant flag to False and allow env var override 2025-01-06 11:28:39 -08:00
activations.py Fix typos 2025-01-19 13:39:40 -08:00
activations_me.py
adaptive_avgmax_pool.py
attention2d.py Fix typos 2025-01-19 13:39:40 -08:00
attention_pool.py Prep for siglip2 release 2025-02-21 13:10:51 -08:00
attention_pool2d.py
blur_pool.py
bottleneck_attn.py
cbam.py
classifier.py
cond_conv2d.py
config.py Update README, few minor fixups. 2025-01-06 13:09:15 -08:00
conv2d_same.py
conv_bn_act.py
create_act.py
create_attn.py
create_conv2d.py
create_norm.py Add SimpleNorm to create_norm factory 2024-12-30 19:24:21 -08:00
create_norm_act.py Fix typos 2025-01-19 13:39:40 -08:00
drop.py
eca.py
evo_norm.py
fast_norm.py Use torch F.rms_norm when possible, select fast vs normal paths appropriately and test with torchscript 2024-12-30 19:24:21 -08:00
filter_response_norm.py
format.py
gather_excite.py
gen_maxpool.py
global_context.py
grid.py
grn.py
halo_attn.py
helpers.py
how_pool.py
hybrid_embed.py
inplace_abn.py
interpolate.py
lambda_layer.py
layer_scale.py
linear.py
lse_pool.py
median_pool.py
mixed_conv2d.py
ml_decoder.py
mlp.py Add comments to MLP layers re expected layouts 2025-01-02 09:41:35 -08:00
non_local_attn.py
norm.py Use torch F.rms_norm when possible, select fast vs normal paths appropriately and test with torchscript 2024-12-30 19:24:21 -08:00
norm_act.py Add missing training flag to convert_sync_batchnorm 2025-01-21 11:51:55 -08:00
padding.py
patch_dropout.py
patch_embed.py fix img_size type 2025-04-18 21:05:05 -07:00
pool2d_same.py
pos_embed.py
pos_embed_rel.py
pos_embed_sincos.py
selective_kernel.py
separable_conv.py
simpool.py
slot_pool.py
space_to_depth.py
split_attn.py
split_batchnorm.py
squeeze_excite.py
std_conv.py
test_time_pool.py
trace_utils.py
typing.py
vit_pool.py
weight_init.py Fix typos 2025-01-19 13:39:40 -08:00