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 43aa84e861 Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)		2 years ago
..
__init__.py	Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)	2 years ago
activations.py	…
activations_jit.py	…
activations_me.py	…
adaptive_avgmax_pool.py	…
attention_pool2d.py	…
blur_pool.py	…
bottleneck_attn.py	…
cbam.py	…
classifier.py	…
cond_conv2d.py	…
config.py	…
conv2d_same.py	…
conv_bn_act.py	Add more experimental darknet and 'cs2' darknet variants (different cross stage setup, closer to newer YOLO backbones) for train trials.	3 years ago
create_act.py	Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)	2 years ago
create_attn.py	Add MobileVitV2 support. Fix #1332. Move GroupNorm1 to common layers (used in poolformer + mobilevitv2). Keep ol custom ConvNeXt LayerNorm2d impl as LayerNormExp2d for reference.	3 years ago
create_conv2d.py	…
create_norm.py	Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)	2 years ago
create_norm_act.py	…
drop.py	Improve repr for DropPath module	3 years ago
eca.py	…
evo_norm.py	Remove SiLU layer in default args that breaks import on old old PyTorch	3 years ago
fast_norm.py	Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)	2 years ago
filter_response_norm.py	…
gather_excite.py	…
global_context.py	…
halo_attn.py	…
helpers.py	Allow ntuple to be used with string values	3 years ago
inplace_abn.py	…
lambda_layer.py	…
linear.py	…
median_pool.py	…
mixed_conv2d.py	…
ml_decoder.py	…
mlp.py	…
non_local_attn.py	…
norm.py	Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)	2 years ago
norm_act.py	Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)	2 years ago
padding.py	…
patch_embed.py	…
pool2d_same.py	…
pos_embed.py	…
selective_kernel.py	…
separable_conv.py	…
space_to_depth.py	…
split_attn.py	…
split_batchnorm.py	…
squeeze_excite.py	Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)	2 years ago
std_conv.py	…
test_time_pool.py	Add --use-train-size flag to force use of train input_size (over test input size) for validation. Default test-time pooling to use train input size (fixes issues).	3 years ago
trace_utils.py	…
weight_init.py	Add eps arg to LayerNorm2d, add 'tf' (tensorflow) variant of trunc_normal_ that applies scale/shift after sampling (instead of needing to move a/b)	3 years ago