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 a5310a3451 Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update		4 years ago
..
__init__.py	Cleanup experimental vit weight init a bit	4 years ago
activations.py	Fix inplace arg compat for GELU and PreLU via activation factory	4 years ago
activations_jit.py	…
activations_me.py	Merge pull request #282 from tigert1998/patch-1	4 years ago
adaptive_avgmax_pool.py	Add 'fast' global pool option, remove redundant SEModule from tresnet, normal one is now 'fast'	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	ResNetV2 pre-act and non-preact model, w/ BiT pretrained weights and support for ViT R50 model. Tweaks for in21k num_classes passing. More to do... tests failing.	4 years ago
cond_conv2d.py	Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.	4 years ago
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 inplace arg compat for GELU and PreLU via activation factory	4 years ago
create_attn.py	Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.	4 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
drop.py	Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.	4 years ago
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	update collections.abc import	4 years ago
inplace_abn.py	Update README, fix iabn pip version print.	4 years ago
linear.py	A few more changes for 0.3.2 maint release. Linear layer change for mobilenetv3 and inception_v3, support no bias for linear wrapper.	4 years ago
median_pool.py	Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.	4 years ago
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
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	…
pool2d_same.py	Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.	4 years ago
se.py	Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.	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	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	…
std_conv.py	Add ECA-NFNet-L0 weights and update model name. Update README and bump version to 0.4.6	4 years ago
test_time_pool.py	Add new weights for ecaresnet26t/50t/269d models. Remove distinction between 't' and 'tn' (tiered models), tn is now t. Add test time img size spec to default cfg.	4 years ago
weight_init.py	Cleanup experimental vit weight init a bit	4 years ago