| .. |
|
__init__.py
|
Merge branch 'master' into densenet_update_and_more
|
2020-05-13 23:34:44 -07:00 |
|
activations.py
|
Re-enable mem-efficient/jit activations after torchscript tests
|
2020-02-10 11:59:36 -08:00 |
|
adaptive_avgmax_pool.py
|
Some TResNet cleanup.
|
2020-04-27 13:21:05 -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
|
Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch
|
2020-02-15 21:18:25 -08:00 |
|
cond_conv2d.py
|
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
|
2020-04-09 01:41:54 -07:00 |
|
conv2d_same.py
|
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
|
2020-04-09 01:41:54 -07:00 |
|
conv_bn_act.py
|
Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.
|
2020-05-04 12:14:43 -07:00 |
|
create_attn.py
|
Fix minor typos in create_attn.py and resnet.py
|
2020-04-07 21:15:57 +09:00 |
|
create_conv2d.py
|
Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases
|
2020-02-10 11:55:03 -08:00 |
|
create_norm_act.py
|
Add norm_act factory method, move JIT of norm layers to factory
|
2020-05-09 22:09:21 -07:00 |
|
drop.py
|
Improve dropblock impl, add fast variant, and better AMP speed, inplace, batchwise... few ResNeSt cleanups
|
2020-05-13 15:17:08 -07:00 |
|
eca.py
|
fix typo in eca
|
2020-04-14 15:20:35 +04:30 |
|
evo_norm.py
|
Add norm_act factory method, move JIT of norm layers to factory
|
2020-05-09 22:09:21 -07:00 |
|
helpers.py
|
Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases
|
2020-02-10 11:55:03 -08:00 |
|
median_pool.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
mixed_conv2d.py
|
Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch
|
2020-02-15 21:18:25 -08:00 |
|
norm_act.py
|
DenseNet converted to support ABN (norm + act) modules. Experimenting with EvoNorm, IABN
|
2020-05-09 18:26:41 -07:00 |
|
padding.py
|
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
|
2020-04-09 01:41:54 -07:00 |
|
pool2d_same.py
|
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
|
2020-04-09 01:41:54 -07:00 |
|
se.py
|
Add RegNet models and weights
|
2020-05-18 00:08:52 -07:00 |
|
selective_kernel.py
|
Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.
|
2020-05-04 12:14:43 -07:00 |
|
space_to_depth.py
|
Remove some CRLF that made it into TResNet merge
|
2020-04-27 13:23:41 -07:00 |
|
split_attn.py
|
Improve dropblock impl, add fast variant, and better AMP speed, inplace, batchwise... few ResNeSt cleanups
|
2020-05-13 15:17:08 -07:00 |
|
split_batchnorm.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
test_time_pool.py
|
Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases
|
2020-02-10 11:55:03 -08:00 |
|
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 |
0ea53cecc3