You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Ross Wightman 4f0f9cb348 Fix #954 by bringing traceable _assert into timm to allow compat w/ PyTorch < 1.8		3 years ago
..
__init__.py	Fix #954 by bringing traceable _assert into timm to allow compat w/ PyTorch < 1.8	3 years ago
activations.py	…
activations_jit.py	…
activations_me.py	…
adaptive_avgmax_pool.py	Refactoring, cleanup, improved test coverage.	3 years ago
attention_pool2d.py	Add initial AttentionPool2d that's being trialed. Fix comment and still trying to improve reliability of sgd test.	3 years ago
blur_pool.py	…
bottleneck_attn.py	Add option to include relative pos embedding in the attention scaling as per references. See discussion #912	3 years ago
cbam.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	3 years ago
classifier.py	Refactoring, cleanup, improved test coverage.	3 years ago
cond_conv2d.py	…
config.py	…
conv2d_same.py	…
conv_bn_act.py	…
create_act.py	Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.	3 years ago
create_attn.py	Update attention / self-attn based models from a series of experiments:	3 years ago
create_conv2d.py	…
create_norm_act.py	…
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.	3 years ago
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.	3 years ago
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.	3 years ago
halo_attn.py	Add weights for regnetz_d and haloregnetz_c, update regnetz_c weights. Add commented PyTorch XLA code for halo attention	3 years ago
helpers.py	Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.	3 years ago
inplace_abn.py	…
lambda_layer.py	Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs	3 years ago
linear.py	…
median_pool.py	…
mixed_conv2d.py	…
mlp.py	Cleanup re-use of Dropout modules in Mlp modules after some twitter feedback :p	3 years ago
non_local_attn.py	Fix torchscript issue in bat	3 years ago
norm.py	Realized LayerNorm2d won't work in all cases as is, fixed.	3 years ago
norm_act.py	…
padding.py	…
patch_embed.py	Fix #954 by bringing traceable _assert into timm to allow compat w/ PyTorch < 1.8	3 years ago
pool2d_same.py	Support npz custom load for vision transformer hybrid models. Add posembed rescale for npz load.	3 years ago
selective_kernel.py	Remove min channels for SelectiveKernel, divisor should cover cases well enough.	3 years ago
separable_conv.py	…
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.	3 years ago
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.	3 years ago
std_conv.py	Use reshape instead of view in std_conv, causing issues in recent PyTorch in channels_last	3 years ago
test_time_pool.py	…
trace_utils.py	Fix #954 by bringing traceable _assert into timm to allow compat w/ PyTorch < 1.8	3 years ago
weight_init.py	…