| .. |
|
__init__.py
|
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
|
2021-05-31 13:18:11 -07:00 |
|
activations.py
|
…
|
|
|
activations_jit.py
|
…
|
|
|
activations_me.py
|
…
|
|
|
adaptive_avgmax_pool.py
|
Refactoring, cleanup, improved test coverage.
|
2021-06-12 16:40:02 -07:00 |
|
blur_pool.py
|
Remove filter hack from BlurPool w/ non-persistent buffer. Use BlurPool2d instead of AntiAliasing.. for TResNet. Breaks PyTorch < 1.6.
|
2021-05-04 16:56:28 -07:00 |
|
bottleneck_attn.py
|
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
|
2021-05-04 21:40:39 -07:00 |
|
cbam.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
classifier.py
|
Refactoring, cleanup, improved test coverage.
|
2021-06-12 16:40:02 -07:00 |
|
cond_conv2d.py
|
…
|
|
|
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.
|
2021-02-09 16:22:52 -08:00 |
|
create_act.py
|
Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
|
2021-05-26 15:28:42 -07:00 |
|
create_attn.py
|
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
|
2021-05-31 13:18:11 -07:00 |
|
create_conv2d.py
|
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354.
|
2021-02-09 16:22:52 -08:00 |
|
create_norm_act.py
|
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
|
2021-02-09 16:22:52 -08:00 |
|
drop.py
|
…
|
|
|
eca.py
|
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
|
2021-05-31 13:18:11 -07:00 |
|
evo_norm.py
|
…
|
|
|
gather_excite.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
global_context.py
|
Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode.
|
2021-08-07 16:45:29 -07:00 |
|
halo_attn.py
|
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
|
2021-05-04 21:40:39 -07:00 |
|
helpers.py
|
Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.
|
2021-05-28 20:47:24 -07:00 |
|
inplace_abn.py
|
Update README, fix iabn pip version print.
|
2021-03-07 16:17:06 -08:00 |
|
involution.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
lambda_layer.py
|
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
|
2021-05-04 21:40:39 -07:00 |
|
linear.py
|
…
|
|
|
median_pool.py
|
…
|
|
|
mixed_conv2d.py
|
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354.
|
2021-02-09 16:22:52 -08:00 |
|
mlp.py
|
Refactoring, cleanup, improved test coverage.
|
2021-06-12 16:40:02 -07:00 |
|
non_local_attn.py
|
Fix torchscript issue in bat
|
2021-06-08 23:19:51 -07:00 |
|
norm.py
|
Realized LayerNorm2d won't work in all cases as is, fixed.
|
2021-07-05 18:21:34 -07:00 |
|
norm_act.py
|
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
|
2021-02-09 16:22:52 -08:00 |
|
padding.py
|
…
|
|
|
patch_embed.py
|
Add levit, levit_c, and visformer model defs. Largely untested and not finished cleanup.
|
2021-05-14 17:16:34 -07:00 |
|
pool2d_same.py
|
Support npz custom load for vision transformer hybrid models. Add posembed rescale for npz load.
|
2021-06-14 12:31:44 -07:00 |
|
selective_kernel.py
|
Remove min channels for SelectiveKernel, divisor should cover cases well enough.
|
2021-05-31 15:38:56 -07:00 |
|
separable_conv.py
|
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
|
2021-02-09 16:22:52 -08:00 |
|
space_to_depth.py
|
…
|
|
|
split_attn.py
|
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
|
2021-05-31 13:18:11 -07:00 |
|
split_batchnorm.py
|
…
|
|
|
squeeze_excite.py
|
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
|
2021-05-31 13:18:11 -07:00 |
|
std_conv.py
|
Add file docstring to std_conv.py
|
2021-06-13 12:31:06 -07:00 |
|
swin_attn.py
|
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
|
2021-05-04 21:40:39 -07:00 |
|
test_time_pool.py
|
…
|
|
|
weight_init.py
|
Cleanup experimental vit weight init a bit
|
2021-03-20 09:44:24 -07:00 |
01cb46a9a5