| .. |
|
__init__.py
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
2020-10-13 13:33:44 -07:00 |
|
activations.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
activations_jit.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
activations_me.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
adaptive_avgmax_pool.py
|
Add 'fast' global pool option, remove redundant SEModule from tresnet, normal one is now 'fast'
|
2020-09-02 09:11:48 -07:00 |
|
anti_aliasing.py
|
Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop
|
2020-05-01 17:00:21 -07:00 |
|
blur_pool.py
|
Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop
|
2020-05-01 17:00:21 -07:00 |
|
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
|
2020-09-01 16:05:32 -07:00 |
|
classifier.py
|
More uniform treatment of classifiers across all models, reduce code duplication.
|
2020-08-03 22:18:24 -07:00 |
|
cond_conv2d.py
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
2020-10-13 13:33:44 -07:00 |
|
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.
|
2020-06-02 21:06:10 -07:00 |
|
conv2d_same.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
conv_bn_act.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
create_act.py
|
Add missing leaky_relu layer factory defn, update Apex/Native loss scaler interfaces to support unscaled grad clipping. Bump ver to 0.2.2 for pending release.
|
2020-10-02 16:19:39 -07:00 |
|
create_attn.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
create_conv2d.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
create_norm_act.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
drop.py
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
2020-10-13 13:33:44 -07:00 |
|
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
|
2020-09-01 16:05:32 -07:00 |
|
evo_norm.py
|
Fix a silly bug in Sample version of EvoNorm missing x* part of swish, update EvoNormBatch to accumulated unbiased variance.
|
2020-08-13 18:25:01 -07:00 |
|
helpers.py
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
2020-10-13 13:33:44 -07:00 |
|
inplace_abn.py
|
Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs.
|
2020-07-13 15:01:06 -07:00 |
|
median_pool.py
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
2020-10-13 13:33:44 -07:00 |
|
mixed_conv2d.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
norm_act.py
|
Switch DPN to use BnAct layer, train a new DPN 68b model with RA to 79.21
|
2020-07-12 11:13:06 -07:00 |
|
padding.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
pool2d_same.py
|
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
|
2020-10-13 13:33:44 -07:00 |
|
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
|
2020-09-01 16:05:32 -07:00 |
|
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
|
2020-09-01 16:05:32 -07:00 |
|
separable_conv.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
space_to_depth.py
|
…
|
|
|
split_attn.py
|
Add ReXNet w/ remapped weights, feature support
|
2020-07-23 10:28:57 -07:00 |
|
split_batchnorm.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
test_time_pool.py
|
More models in sotabench, more control over sotabench run, dataset filename extraction consistency
|
2020-09-24 15:56:57 -07:00 |
|
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.
|
2020-05-12 21:59:34 -07:00 |
f31933cb37