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.
pytorch-image-models/timm/models/layers
Ross Wightman 298fba09ac
Back out some activation hacks trialing upcoming pytorch changes
4 years ago
..
__init__.py Lots of changes to model creation helpers, close to finalizing feature extraction / interfaces 4 years ago
activations.py Back out some activation hacks trialing upcoming pytorch changes 4 years ago
activations_jit.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
activations_me.py Add custom grad tests, fix cut & paste error with hard_mish ME, add a few more pytorch act fns to factory 4 years ago
adaptive_avgmax_pool.py Some TResNet cleanup. 5 years ago
anti_aliasing.py Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop 5 years ago
blur_pool.py Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop 5 years ago
cbam.py Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch 5 years ago
classifier.py Lots of changes to model creation helpers, close to finalizing feature extraction / interfaces 4 years ago
cond_conv2d.py Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit. 5 years ago
config.py Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit. 5 years ago
conv2d_same.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
conv_bn_act.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
create_act.py Back out some activation hacks trialing upcoming pytorch changes 4 years ago
create_attn.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
create_conv2d.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
create_norm_act.py Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs. 4 years ago
drop.py Significant ResNet refactor: 4 years ago
eca.py fix typo in eca 5 years ago
evo_norm.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
helpers.py Lots of changes to model creation helpers, close to finalizing feature extraction / interfaces 4 years ago
inplace_abn.py Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs. 4 years ago
median_pool.py Big move, layer modules and fn to timm/models/layers 5 years ago
mixed_conv2d.py Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch 5 years ago
norm_act.py Switch DPN to use BnAct layer, train a new DPN 68b model with RA to 79.21 4 years ago
padding.py Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well. 5 years ago
pool2d_same.py Fix a few issues that came up in tests 4 years ago
se.py Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs. 4 years ago
selective_kernel.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
separable_conv.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
space_to_depth.py Remove some CRLF that made it into TResNet merge 5 years ago
split_attn.py Improve dropblock impl, add fast variant, and better AMP speed, inplace, batchwise... few ResNeSt cleanups 5 years ago
split_batchnorm.py Big move, layer modules and fn to timm/models/layers 5 years ago
test_time_pool.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
weight_init.py Remove annoying InceptionV3 dependency on scipy and insanely slow trunc_norm init. Bring InceptionV3 code into this codebase and use upcoming torch trunch_norm_ init. 5 years ago