pytorch-image-models

History

Ross Wightman 93cc08fdc5 Make evonorm variables 1d to match other PyTorch norm layers, will break weight compat for any existing use (likely minimal, easy to fix).		4 years ago
..
__init__.py	Fix #954 by bringing traceable _assert into timm to allow compat w/ PyTorch < 1.8	4 years ago
activations.py	…
activations_jit.py	…
activations_me.py	…
adaptive_avgmax_pool.py	…
attention_pool2d.py	Add initial AttentionPool2d that's being trialed. Fix comment and still trying to improve reliability of sgd test.	4 years ago
blur_pool.py	…
bottleneck_attn.py	wip - pre-rebase	4 years ago
cbam.py	…
classifier.py	…
cond_conv2d.py	…
config.py	…
conv2d_same.py	…
conv_bn_act.py	…
create_act.py	…
create_attn.py	…
create_conv2d.py	…
create_norm_act.py	…
drop.py	…
eca.py	…
evo_norm.py	Make evonorm variables 1d to match other PyTorch norm layers, will break weight compat for any existing use (likely minimal, easy to fix).	4 years ago
gather_excite.py	…
global_context.py	wip - pre-rebase	4 years ago
halo_attn.py	wip - pre-rebase	4 years ago
helpers.py	…
inplace_abn.py	…
lambda_layer.py	wip - pre-rebase	4 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	4 years ago
non_local_attn.py	wip - pre-rebase	4 years ago
norm.py	Add ResNet-50 w/ GN (resnet50_gn) and SEBotNet-33-TS (sebotnet33ts_256) model defs and weights. Update halonet50ts weights w/ slightly better variant in1k val, more robust to test sets.	4 years ago
norm_act.py	Prep a set of ResNetV2 models with GroupNorm, EvoNormB0, EvoNormS0 for BN free model experiments on TPU and IPU	4 years ago
padding.py	…
patch_embed.py	wip - attempting to rebase	4 years ago
pool2d_same.py	…
selective_kernel.py	wip - pre-rebase	4 years ago
separable_conv.py	…
space_to_depth.py	…
split_attn.py	…
split_batchnorm.py	…
squeeze_excite.py	…
std_conv.py	Use reshape instead of view in std_conv, causing issues in recent PyTorch in channels_last	4 years ago
test_time_pool.py	…
trace_utils.py	Better fix for #954 that doesn't break torchscript, pull torch._assert into timm namespace when it exists	4 years ago
weight_init.py	…