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 621e1b2182 Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.		2 years ago
..
__init__.py	Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.	2 years ago
activations.py	…
activations_jit.py	…
activations_me.py	…
adaptive_avgmax_pool.py	…
attention_pool2d.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
blur_pool.py	…
bottleneck_attn.py	…
cbam.py	…
classifier.py	Factor NormMlpClassifierHead from MaxxViT and use across MaxxViT / ConvNeXt / DaViT, refactor some type hints & comments	2 years ago
cond_conv2d.py	…
config.py	…
conv2d_same.py	…
conv_bn_act.py	…
create_act.py	…
create_attn.py	…
create_conv2d.py	…
create_norm.py	Add EfficientFormer-V2, refactor EfficientFormer and Levit for more uniformity across the 3 related arch. Add features_out support to levit conv models and efficientformer_v2. All weights on hub.	2 years ago
create_norm_act.py	…
drop.py	…
eca.py	…
evo_norm.py	…
fast_norm.py	Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.	2 years ago
filter_response_norm.py	…
gather_excite.py	…
global_context.py	…
grn.py	Add ConvNeXt-V2 support (model additions and weights) (#1614)	2 years ago
halo_attn.py	…
helpers.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
inplace_abn.py	…
lambda_layer.py	…
linear.py	…
median_pool.py	…
mixed_conv2d.py	…
ml_decoder.py	…
mlp.py	Add ConvNeXt-V2 support (model additions and weights) (#1614)	2 years ago
non_local_attn.py	…
norm.py	Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.	2 years ago
norm_act.py	Update batchnorm freezing to handle NormAct variants, Add GroupNorm1Act, update BatchNormAct2d tracing change from PyTorch	2 years ago
padding.py	…
patch_embed.py	Better vmap compat across recent torch versions	2 years ago
pool2d_same.py	…
pos_embed.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
pos_embed_rel.py	Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.	2 years ago
pos_embed_sincos.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
selective_kernel.py	…
separable_conv.py	…
space_to_depth.py	…
split_attn.py	…
split_batchnorm.py	…
squeeze_excite.py	…
std_conv.py	…
test_time_pool.py	…
trace_utils.py	…
weight_init.py	…