Ross Wightman 131518c15c Add comments to MLP layers re expected layouts		2025-01-02 09:41:35 -08:00
..
__init__.py	Fixing RmsNorm to fix #2380 and noticed with aimv2 when comparing outputs. Still some work to do, need to look at AMP / fast mode behaviour, dispatch to torch when possible. Add SimpleNorm for 'LayerNorm w/o centering and bias'	2024-12-30 19:24:21 -08:00
activations.py	…
activations_me.py	…
adaptive_avgmax_pool.py	…
attention2d.py	Merge branch 'main' into fix-mqa-v2	2025-01-02 00:11:22 +01:00
attention_pool.py	…
attention_pool2d.py	…
blur_pool.py	…
bottleneck_attn.py	…
cbam.py	…
classifier.py	More Hiera updates. Add forward_intermediates to hieradat/sam2 impl. Make both use same classifier module. Add coarse bool to intermediates.	2024-08-16 11:10:04 -07:00
cond_conv2d.py	…
config.py	…
conv2d_same.py	…
conv_bn_act.py	See if we can avoid some model / layer pickle issues with the aa attr in ConvNormAct	2024-12-03 08:02:55 -08:00
create_act.py	Add WIP HieraDet impl (SAM2 backbone support)	2024-08-15 17:58:15 -07:00
create_attn.py	…
create_conv2d.py	…
create_norm.py	Add SimpleNorm to create_norm factory	2024-12-30 19:24:21 -08:00
create_norm_act.py	…
drop.py	…
eca.py	…
evo_norm.py	…
fast_norm.py	Use torch F.rms_norm when possible, select fast vs normal paths appropriately and test with torchscript	2024-12-30 19:24:21 -08:00
filter_response_norm.py	…
format.py	…
gather_excite.py	…
global_context.py	…
grid.py	…
grn.py	…
halo_attn.py	…
helpers.py	…
hybrid_embed.py	…
inplace_abn.py	…
interpolate.py	…
lambda_layer.py	…
layer_scale.py	Fix hiera init with num_classes=0, fix weight tag names for sbb2 hiera/vit weights, add LayerScale/LayerScale2d to layers	2024-08-15 11:14:38 -07:00
linear.py	…
median_pool.py	…
mixed_conv2d.py	…
ml_decoder.py	…
mlp.py	Add comments to MLP layers re expected layouts	2025-01-02 09:41:35 -08:00
non_local_attn.py	…
norm.py	Use torch F.rms_norm when possible, select fast vs normal paths appropriately and test with torchscript	2024-12-30 19:24:21 -08:00
norm_act.py	…
padding.py	…
patch_dropout.py	…
patch_embed.py	…
pool2d_same.py	…
pos_embed.py	…
pos_embed_rel.py	…
pos_embed_sincos.py	…
selective_kernel.py	…
separable_conv.py	…
space_to_depth.py	…
split_attn.py	…
split_batchnorm.py	…
squeeze_excite.py	…
std_conv.py	…
test_time_pool.py	…
trace_utils.py	…
typing.py	…
weight_init.py	Rename global pos embed for Hiera abswin, factor out commonly used vit weight init fns to layers. Add a channels-last ver of normmlp head.	2024-08-15 17:46:36 -07:00