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 110a7c4982 AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992		4 years ago
..
__init__.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
activations.py	…
activations_jit.py	…
activations_me.py	…
adaptive_avgmax_pool.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
anti_aliasing.py	…
blur_pool.py	…
cbam.py	AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992	4 years ago
classifier.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 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_act.py	…
drop.py	…
eca.py	AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992	4 years ago
evo_norm.py	Fix a silly bug in Sample version of EvoNorm missing x* part of swish, update EvoNormBatch to accumulated unbiased variance.	4 years ago
helpers.py	…
inplace_abn.py	…
median_pool.py	…
mixed_conv2d.py	…
norm_act.py	…
padding.py	…
pool2d_same.py	…
se.py	AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992	4 years ago
selective_kernel.py	AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992	4 years ago
separable_conv.py	…
space_to_depth.py	…
split_attn.py	…
split_batchnorm.py	…
test_time_pool.py	…
weight_init.py	…