| .. |
|
__init__.py
|
include typing suggestions by @rwightman
|
2023-10-30 13:47:54 -07:00 |
|
activations.py
|
Add quickgelu vit clip variants, simplify get_norm_layer and allow string args in vit norm/act. Add metaclip CLIP weights
|
2023-11-03 11:01:41 -07:00 |
|
activations_jit.py
|
…
|
|
|
activations_me.py
|
…
|
|
|
adaptive_avgmax_pool.py
|
fix adaptive_avgmax_pool.py
|
2023-10-29 23:03:36 -07:00 |
|
attention_pool.py
|
Add SigLIP weights
|
2023-10-16 23:26:08 -07:00 |
|
attention_pool2d.py
|
…
|
|
|
blur_pool.py
|
…
|
|
|
bottleneck_attn.py
|
…
|
|
|
cbam.py
|
…
|
|
|
classifier.py
|
Final push to get remaining models using multi-weight pretrained configs, almost all weights on HF hub
|
2023-04-26 15:52:13 -07:00 |
|
cond_conv2d.py
|
…
|
|
|
config.py
|
fast_attn -> fused_attn, implement global config for enable/disable fused_attn, add to more models. vit clip openai 336 weights.
|
2023-04-10 12:04:33 -07:00 |
|
conv2d_same.py
|
Add onnx utils and export code, tweak padding and conv2d_same for better dynamic export with recent PyTorch
|
2023-04-11 17:03:57 -07:00 |
|
conv_bn_act.py
|
Final push to get remaining models using multi-weight pretrained configs, almost all weights on HF hub
|
2023-04-26 15:52:13 -07:00 |
|
create_act.py
|
Consistency handling None / empty string inputs to norm / act create fns
|
2023-11-03 11:01:41 -07:00 |
|
create_attn.py
|
…
|
|
|
create_conv2d.py
|
…
|
|
|
create_norm.py
|
Fix break of 2 years old torchvision installs :/
|
2023-11-04 02:32:09 -07:00 |
|
create_norm_act.py
|
Consistency handling None / empty string inputs to norm / act create fns
|
2023-11-03 11:01:41 -07:00 |
|
drop.py
|
…
|
|
|
eca.py
|
…
|
|
|
evo_norm.py
|
…
|
|
|
fast_norm.py
|
Metaformer baselines for vision (final PR with cleanup) (#1793)
|
2023-05-05 11:18:26 -07:00 |
|
filter_response_norm.py
|
…
|
|
|
format.py
|
All swin models support spatial output, add output_fmt to v1/v2 and use ClassifierHead.
|
2023-03-15 23:21:51 -07:00 |
|
gather_excite.py
|
…
|
|
|
global_context.py
|
…
|
|
|
grn.py
|
…
|
|
|
halo_attn.py
|
…
|
|
|
helpers.py
|
Fixed Typos
|
2023-10-21 21:46:31 -07:00 |
|
inplace_abn.py
|
…
|
|
|
interpolate.py
|
Add more advanced interpolation method from BEiT and support non-square window & image size adaptation for
|
2023-08-08 16:41:16 -07:00 |
|
lambda_layer.py
|
…
|
|
|
linear.py
|
…
|
|
|
median_pool.py
|
…
|
|
|
mixed_conv2d.py
|
…
|
|
|
ml_decoder.py
|
…
|
|
|
mlp.py
|
Removing unused self.drop
|
2023-10-05 11:20:57 -07:00 |
|
non_local_attn.py
|
…
|
|
|
norm.py
|
Torchscript fixes/hacks for rms_norm, refactor ParallelScalingBlock with manual combination of input projections, closer paper match
|
2023-02-16 16:57:42 -08:00 |
|
norm_act.py
|
Final push to get remaining models using multi-weight pretrained configs, almost all weights on HF hub
|
2023-04-26 15:52:13 -07:00 |
|
padding.py
|
Add onnx utils and export code, tweak padding and conv2d_same for better dynamic export with recent PyTorch
|
2023-04-11 17:03:57 -07:00 |
|
patch_dropout.py
|
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
|
2023-04-07 20:27:23 -07:00 |
|
patch_embed.py
|
Add device arg for patch embed resize, fix #2024
|
2023-12-04 11:42:13 -08:00 |
|
pool2d_same.py
|
…
|
|
|
pos_embed.py
|
Move levit style pos bias resize with other rel pos bias utils
|
2023-09-01 11:05:56 -07:00 |
|
pos_embed_rel.py
|
Move levit style pos bias resize with other rel pos bias utils
|
2023-09-01 11:05:56 -07:00 |
|
pos_embed_sincos.py
|
Support dynamic_resize in eva.py models
|
2023-08-27 15:58:35 -07:00 |
|
selective_kernel.py
|
…
|
|
|
separable_conv.py
|
…
|
|
|
space_to_depth.py
|
Always some torchscript issues
|
2023-04-26 20:42:34 -07:00 |
|
split_attn.py
|
…
|
|
|
split_batchnorm.py
|
…
|
|
|
squeeze_excite.py
|
…
|
|
|
std_conv.py
|
…
|
|
|
test_time_pool.py
|
…
|
|
|
trace_utils.py
|
…
|
|
|
typing.py
|
include suggestions from review
|
2023-10-30 13:47:54 -07:00 |
|
weight_init.py
|
…
|
|
