PyTorch Image Models
❗Updates after Oct 10, 2022 are available in version >= 0.9❗
timm.models.layers
moved to timm.layers
:
from timm.models.layers import name
will still work via deprecation mapping (but please transition to timm.layers
).import timm.models.layers.module
or from timm.models.layers.module import name
needs to be changed now.timm.models
have a _
prefix added, ie timm.models.helpers
-> timm.models._helpers
, there are temporary deprecation mapping files but those will be removed.architecture.pretrained_tag
naming (ex resnet50.rsb_a1
).
architecture
defaults to the first weights in the default_cfgs for that model architecture.vit_base_patch16_224_in21k
-> vit_base_patch16_224.augreg_in21k
). There are deprecation mappings for these.features_only=True
, there are checkpoint_filter_fn
methods in any model module that was remapped. These can be passed to timm.models.load_checkpoint(..., filter_fn=timm.models.swin_transformer_v2.checkpoint_filter_fn)
to remap your existing checkpoint.timm
weights. Model cards include link to papers, original source, license.model_args
config entry. model_args
will be passed as kwargs through to models on creation.
vision_transformer.py
typing and doc cleanup by Laureηtquickgelu
ViT variants for OpenAI, DFN, MetaCLIP weights that use it (less efficient)convnext_xxlarge
vision_transformer.py
.
vision_transformer.py
, vision_transformer_hybrid.py
, deit.py
, and eva.py
w/o breaking backward compat.
dynamic_img_size=True
to args at model creation time to allow changing the grid size (interpolate abs and/or ROPE pos embed each forward pass).dynamic_img_pad=True
to allow image sizes that aren't divisible by patch size (pad bottom right to patch size each forward pass).img_size
(interpolate pretrained embed weights once) on creation still works.patch_size
(resize pretrained patch_embed weights once) on creation still works.python validate.py /imagenet --model vit_base_patch16_224 --amp --amp-dtype bfloat16 --img-size 255 --crop-pct 1.0 --model-kwargs dynamic_img_size=True dyamic_img_pad=True
--reparam
arg to benchmark.py
, onnx_export.py
, and validate.py
to trigger layer reparameterization / fusion for models with any one of reparameterize()
, switch_to_deploy()
or fuse()
python validate.py /imagenet --model swin_base_patch4_window7_224.ms_in22k_ft_in1k --amp --amp-dtype bfloat16 --input-size 3 256 320 --model-kwargs window_size=8,10 img_size=256,320
selecsls*
model naming regressionseresnextaa201d_32x8d.sw_in12k_ft_in1k_384
weights (and .sw_in12k
pretrain) with 87.3% top-1 on ImageNet-1k, best ImageNet ResNet family model I'm aware of.timm
0.9 released, transition from 0.8.xdev releasestimm
get_intermediate_layers
function on vit/deit models for grabbing hidden states (inspired by DINO impl). This is WIP and may change significantly... feedback welcome.pretrained=True
and no weights exist (instead of continuing with random initialization)bnb
prefix, ie bnbadam8bit
timm
out of pre-release statetimm
models uploaded to HF Hub and almost all updated to support multi-weight pretrained configs--grad-accum-steps
), thanks Taeksang Kim--head-init-scale
and --head-init-bias
to train.py to scale classiifer head and set fixed bias for fine-tuneinplace_abn
) use, replaced use in tresnet with standard BatchNorm (modified weights accordingly).drop_rate
(classifier dropout), proj_drop_rate
(block mlp / out projections), pos_drop_rate
(position embedding drop), attn_drop_rate
(attention dropout). Also add patch dropout (FLIP) to vit and eva models.timm
trained weights added with recipe based tags to differentiateresnetaa50d.sw_in12k_ft_in1k
- 81.7 @ 224, 82.6 @ 288resnetaa101d.sw_in12k_ft_in1k
- 83.5 @ 224, 84.1 @ 288seresnextaa101d_32x8d.sw_in12k_ft_in1k
- 86.0 @ 224, 86.5 @ 288seresnextaa101d_32x8d.sw_in12k_ft_in1k_288
- 86.5 @ 288, 86.7 @ 320model | top1 | top5 | img_size | param_count | gmacs | macts |
---|---|---|---|---|---|---|
convnext_xxlarge.clip_laion2b_soup_ft_in1k | 88.612 | 98.704 | 256 | 846.47 | 198.09 | 124.45 |
convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384 | 88.312 | 98.578 | 384 | 200.13 | 101.11 | 126.74 |
convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320 | 87.968 | 98.47 | 320 | 200.13 | 70.21 | 88.02 |
convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384 | 87.138 | 98.212 | 384 | 88.59 | 45.21 | 84.49 |
convnext_base.clip_laion2b_augreg_ft_in12k_in1k | 86.344 | 97.97 | 256 | 88.59 | 20.09 | 37.55 |
model | top1 | top5 | param_count | img_size |
---|---|---|---|---|
eva02_large_patch14_448.mim_m38m_ft_in22k_in1k | 90.054 | 99.042 | 305.08 | 448 |
eva02_large_patch14_448.mim_in22k_ft_in22k_in1k | 89.946 | 99.01 | 305.08 | 448 |
eva_giant_patch14_560.m30m_ft_in22k_in1k | 89.792 | 98.992 | 1014.45 | 560 |
eva02_large_patch14_448.mim_in22k_ft_in1k | 89.626 | 98.954 | 305.08 | 448 |
eva02_large_patch14_448.mim_m38m_ft_in1k | 89.57 | 98.918 | 305.08 | 448 |
eva_giant_patch14_336.m30m_ft_in22k_in1k | 89.56 | 98.956 | 1013.01 | 336 |
eva_giant_patch14_336.clip_ft_in1k | 89.466 | 98.82 | 1013.01 | 336 |
eva_large_patch14_336.in22k_ft_in22k_in1k | 89.214 | 98.854 | 304.53 | 336 |
eva_giant_patch14_224.clip_ft_in1k | 88.882 | 98.678 | 1012.56 | 224 |
eva02_base_patch14_448.mim_in22k_ft_in22k_in1k | 88.692 | 98.722 | 87.12 | 448 |
eva_large_patch14_336.in22k_ft_in1k | 88.652 | 98.722 | 304.53 | 336 |
eva_large_patch14_196.in22k_ft_in22k_in1k | 88.592 | 98.656 | 304.14 | 196 |
eva02_base_patch14_448.mim_in22k_ft_in1k | 88.23 | 98.564 | 87.12 | 448 |
eva_large_patch14_196.in22k_ft_in1k | 87.934 | 98.504 | 304.14 | 196 |
eva02_small_patch14_336.mim_in22k_ft_in1k | 85.74 | 97.614 | 22.13 | 336 |
eva02_tiny_patch14_336.mim_in22k_ft_in1k | 80.658 | 95.524 | 5.76 | 336 |
regnet.py
, rexnet.py
, byobnet.py
, resnetv2.py
, swin_transformer.py
, swin_transformer_v2.py
, swin_transformer_v2_cr.py
swinv2_cr_*
, and NHWC for all others) and spatial embedding outputs.timm
weights:
rexnetr_200.sw_in12k_ft_in1k
- 82.6 @ 224, 83.2 @ 288rexnetr_300.sw_in12k_ft_in1k
- 84.0 @ 224, 84.5 @ 288regnety_120.sw_in12k_ft_in1k
- 85.0 @ 224, 85.4 @ 288regnety_160.lion_in12k_ft_in1k
- 85.6 @ 224, 86.0 @ 288regnety_160.sw_in12k_ft_in1k
- 85.6 @ 224, 86.0 @ 288 (compare to SWAG PT + 1k FT this is same BUT much lower res, blows SEER FT away)convnext_xxlarge
default LayerNorm eps to 1e-5 (for CLIP weights, improved stability)convnext_large_mlp.clip_laion2b_ft_320
and convnext_lage_mlp.clip_laion2b_ft_soup_320
CLIP image tower weights for features & fine-tunesafetensor
checkpoint support addedvit_*
, vit_relpos*
, coatnet
/ maxxvit
(to start)features_only=True
convnext_base.clip_laion2b_augreg_ft_in1k
- 86.2% @ 256x256convnext_base.clip_laiona_augreg_ft_in1k_384
- 86.5% @ 384x384convnext_large_mlp.clip_laion2b_augreg_ft_in1k
- 87.3% @ 256x256convnext_large_mlp.clip_laion2b_augreg_ft_in1k_384
- 87.9% @ 384x384features_only=True
. Adapted from https://github.com/dingmyu/davit by Fredo.features_only=True
.features_only=True
support to new conv
variants, weight remap required./results
to timm/data/_info
.timm
inference.py
to use, try: python inference.py /folder/to/images --model convnext_small.in12k --label-type detail --topk 5
Add two convnext 12k -> 1k fine-tunes at 384x384
convnext_tiny.in12k_ft_in1k_384
- 85.1 @ 384convnext_small.in12k_ft_in1k_384
- 86.2 @ 384Push all MaxxViT weights to HF hub, and add new ImageNet-12k -> 1k fine-tunes for rw
base MaxViT and CoAtNet 1/2 models
model | top1 | top5 | samples / sec | Params (M) | GMAC | Act (M) |
---|---|---|---|---|---|---|
maxvit_xlarge_tf_512.in21k_ft_in1k | 88.53 | 98.64 | 21.76 | 475.77 | 534.14 | 1413.22 |
maxvit_xlarge_tf_384.in21k_ft_in1k | 88.32 | 98.54 | 42.53 | 475.32 | 292.78 | 668.76 |
maxvit_base_tf_512.in21k_ft_in1k | 88.20 | 98.53 | 50.87 | 119.88 | 138.02 | 703.99 |
maxvit_large_tf_512.in21k_ft_in1k | 88.04 | 98.40 | 36.42 | 212.33 | 244.75 | 942.15 |
maxvit_large_tf_384.in21k_ft_in1k | 87.98 | 98.56 | 71.75 | 212.03 | 132.55 | 445.84 |
maxvit_base_tf_384.in21k_ft_in1k | 87.92 | 98.54 | 104.71 | 119.65 | 73.80 | 332.90 |
maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k | 87.81 | 98.37 | 106.55 | 116.14 | 70.97 | 318.95 |
maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k | 87.47 | 98.37 | 149.49 | 116.09 | 72.98 | 213.74 |
coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k | 87.39 | 98.31 | 160.80 | 73.88 | 47.69 | 209.43 |
maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k | 86.89 | 98.02 | 375.86 | 116.14 | 23.15 | 92.64 |
maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k | 86.64 | 98.02 | 501.03 | 116.09 | 24.20 | 62.77 |
maxvit_base_tf_512.in1k | 86.60 | 97.92 | 50.75 | 119.88 | 138.02 | 703.99 |
coatnet_2_rw_224.sw_in12k_ft_in1k | 86.57 | 97.89 | 631.88 | 73.87 | 15.09 | 49.22 |
maxvit_large_tf_512.in1k | 86.52 | 97.88 | 36.04 | 212.33 | 244.75 | 942.15 |
coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k | 86.49 | 97.90 | 620.58 | 73.88 | 15.18 | 54.78 |
maxvit_base_tf_384.in1k | 86.29 | 97.80 | 101.09 | 119.65 | 73.80 | 332.90 |
maxvit_large_tf_384.in1k | 86.23 | 97.69 | 70.56 | 212.03 | 132.55 | 445.84 |
maxvit_small_tf_512.in1k | 86.10 | 97.76 | 88.63 | 69.13 | 67.26 | 383.77 |
maxvit_tiny_tf_512.in1k | 85.67 | 97.58 | 144.25 | 31.05 | 33.49 | 257.59 |
maxvit_small_tf_384.in1k | 85.54 | 97.46 | 188.35 | 69.02 | 35.87 | 183.65 |
maxvit_tiny_tf_384.in1k | 85.11 | 97.38 | 293.46 | 30.98 | 17.53 | 123.42 |
maxvit_large_tf_224.in1k | 84.93 | 96.97 | 247.71 | 211.79 | 43.68 | 127.35 |
coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k | 84.90 | 96.96 | 1025.45 | 41.72 | 8.11 | 40.13 |
maxvit_base_tf_224.in1k | 84.85 | 96.99 | 358.25 | 119.47 | 24.04 | 95.01 |
maxxvit_rmlp_small_rw_256.sw_in1k | 84.63 | 97.06 | 575.53 | 66.01 | 14.67 | 58.38 |
coatnet_rmlp_2_rw_224.sw_in1k | 84.61 | 96.74 | 625.81 | 73.88 | 15.18 | 54.78 |
maxvit_rmlp_small_rw_224.sw_in1k | 84.49 | 96.76 | 693.82 | 64.90 | 10.75 | 49.30 |
maxvit_small_tf_224.in1k | 84.43 | 96.83 | 647.96 | 68.93 | 11.66 | 53.17 |
maxvit_rmlp_tiny_rw_256.sw_in1k | 84.23 | 96.78 | 807.21 | 29.15 | 6.77 | 46.92 |
coatnet_1_rw_224.sw_in1k | 83.62 | 96.38 | 989.59 | 41.72 | 8.04 | 34.60 |
maxvit_tiny_rw_224.sw_in1k | 83.50 | 96.50 | 1100.53 | 29.06 | 5.11 | 33.11 |
maxvit_tiny_tf_224.in1k | 83.41 | 96.59 | 1004.94 | 30.92 | 5.60 | 35.78 |
coatnet_rmlp_1_rw_224.sw_in1k | 83.36 | 96.45 | 1093.03 | 41.69 | 7.85 | 35.47 |
maxxvitv2_nano_rw_256.sw_in1k | 83.11 | 96.33 | 1276.88 | 23.70 | 6.26 | 23.05 |
maxxvit_rmlp_nano_rw_256.sw_in1k | 83.03 | 96.34 | 1341.24 | 16.78 | 4.37 | 26.05 |
maxvit_rmlp_nano_rw_256.sw_in1k | 82.96 | 96.26 | 1283.24 | 15.50 | 4.47 | 31.92 |
maxvit_nano_rw_256.sw_in1k | 82.93 | 96.23 | 1218.17 | 15.45 | 4.46 | 30.28 |
coatnet_bn_0_rw_224.sw_in1k | 82.39 | 96.19 | 1600.14 | 27.44 | 4.67 | 22.04 |
coatnet_0_rw_224.sw_in1k | 82.39 | 95.84 | 1831.21 | 27.44 | 4.43 | 18.73 |
coatnet_rmlp_nano_rw_224.sw_in1k | 82.05 | 95.87 | 2109.09 | 15.15 | 2.62 | 20.34 |
coatnext_nano_rw_224.sw_in1k | 81.95 | 95.92 | 2525.52 | 14.70 | 2.47 | 12.80 |
coatnet_nano_rw_224.sw_in1k | 81.70 | 95.64 | 2344.52 | 15.14 | 2.41 | 15.41 |
maxvit_rmlp_pico_rw_256.sw_in1k | 80.53 | 95.21 | 1594.71 | 7.52 | 1.85 | 24.86 |
.in12k
tags)
convnext_nano.in12k_ft_in1k
- 82.3 @ 224, 82.9 @ 288 (previously released)convnext_tiny.in12k_ft_in1k
- 84.2 @ 224, 84.5 @ 288convnext_small.in12k_ft_in1k
- 85.2 @ 224, 85.3 @ 288--model-kwargs
and --opt-kwargs
to scripts to pass through rare args directly to model classes from cmd line
train.py /imagenet --model resnet50 --amp --model-kwargs output_stride=16 act_layer=silu
train.py /imagenet --model vit_base_patch16_clip_224 --img-size 240 --amp --model-kwargs img_size=240 patch_size=12
convnext.py
efficientnet_b5.in12k_ft_in1k
- 85.9 @ 448x448vit_medium_patch16_gap_384.in12k_ft_in1k
- 85.5 @ 384x384vit_medium_patch16_gap_256.in12k_ft_in1k
- 84.5 @ 256x256convnext_nano.in12k_ft_in1k
- 82.9 @ 288x288vision_transformer.py
, MAE style ViT-L/14 MIM pretrain w/ EVA-CLIP targets, FT on ImageNet-1k (w/ ImageNet-22k intermediate for some)
model | top1 | param_count | gmac | macts | hub |
---|---|---|---|---|---|
eva_large_patch14_336.in22k_ft_in22k_in1k | 89.2 | 304.5 | 191.1 | 270.2 | link |
eva_large_patch14_336.in22k_ft_in1k | 88.7 | 304.5 | 191.1 | 270.2 | link |
eva_large_patch14_196.in22k_ft_in22k_in1k | 88.6 | 304.1 | 61.6 | 63.5 | link |
eva_large_patch14_196.in22k_ft_in1k | 87.9 | 304.1 | 61.6 | 63.5 | link |
beit.py
.
model | top1 | param_count | gmac | macts | hub |
---|---|---|---|---|---|
eva_giant_patch14_560.m30m_ft_in22k_in1k | 89.8 | 1014.4 | 1906.8 | 2577.2 | link |
eva_giant_patch14_336.m30m_ft_in22k_in1k | 89.6 | 1013 | 620.6 | 550.7 | link |
eva_giant_patch14_336.clip_ft_in1k | 89.4 | 1013 | 620.6 | 550.7 | link |
eva_giant_patch14_224.clip_ft_in1k | 89.1 | 1012.6 | 267.2 | 192.6 | link |
0.8.0dev0
) of multi-weight support (model_arch.pretrained_tag
). Install with pip install --pre timm
--torchcompile
argumentmodel | top1 | param_count | gmac | macts | hub |
---|---|---|---|---|---|
vit_huge_patch14_clip_336.laion2b_ft_in12k_in1k | 88.6 | 632.5 | 391 | 407.5 | link |
vit_large_patch14_clip_336.openai_ft_in12k_in1k | 88.3 | 304.5 | 191.1 | 270.2 | link |
vit_huge_patch14_clip_224.laion2b_ft_in12k_in1k | 88.2 | 632 | 167.4 | 139.4 | link |
vit_large_patch14_clip_336.laion2b_ft_in12k_in1k | 88.2 | 304.5 | 191.1 | 270.2 | link |
vit_large_patch14_clip_224.openai_ft_in12k_in1k | 88.2 | 304.2 | 81.1 | 88.8 | link |
vit_large_patch14_clip_224.laion2b_ft_in12k_in1k | 87.9 | 304.2 | 81.1 | 88.8 | link |
vit_large_patch14_clip_224.openai_ft_in1k | 87.9 | 304.2 | 81.1 | 88.8 | link |
vit_large_patch14_clip_336.laion2b_ft_in1k | 87.9 | 304.5 | 191.1 | 270.2 | link |
vit_huge_patch14_clip_224.laion2b_ft_in1k | 87.6 | 632 | 167.4 | 139.4 | link |
vit_large_patch14_clip_224.laion2b_ft_in1k | 87.3 | 304.2 | 81.1 | 88.8 | link |
vit_base_patch16_clip_384.laion2b_ft_in12k_in1k | 87.2 | 86.9 | 55.5 | 101.6 | link |
vit_base_patch16_clip_384.openai_ft_in12k_in1k | 87 | 86.9 | 55.5 | 101.6 | link |
vit_base_patch16_clip_384.laion2b_ft_in1k | 86.6 | 86.9 | 55.5 | 101.6 | link |
vit_base_patch16_clip_384.openai_ft_in1k | 86.2 | 86.9 | 55.5 | 101.6 | link |
vit_base_patch16_clip_224.laion2b_ft_in12k_in1k | 86.2 | 86.6 | 17.6 | 23.9 | link |
vit_base_patch16_clip_224.openai_ft_in12k_in1k | 85.9 | 86.6 | 17.6 | 23.9 | link |
vit_base_patch32_clip_448.laion2b_ft_in12k_in1k | 85.8 | 88.3 | 17.9 | 23.9 | link |
vit_base_patch16_clip_224.laion2b_ft_in1k | 85.5 | 86.6 | 17.6 | 23.9 | link |
vit_base_patch32_clip_384.laion2b_ft_in12k_in1k | 85.4 | 88.3 | 13.1 | 16.5 | link |
vit_base_patch16_clip_224.openai_ft_in1k | 85.3 | 86.6 | 17.6 | 23.9 | link |
vit_base_patch32_clip_384.openai_ft_in12k_in1k | 85.2 | 88.3 | 13.1 | 16.5 | link |
vit_base_patch32_clip_224.laion2b_ft_in12k_in1k | 83.3 | 88.2 | 4.4 | 5 | link |
vit_base_patch32_clip_224.laion2b_ft_in1k | 82.6 | 88.2 | 4.4 | 5 | link |
vit_base_patch32_clip_224.openai_ft_in1k | 81.9 | 88.2 | 4.4 | 5 | link |
model | top1 | param_count | gmac | macts | hub |
---|---|---|---|---|---|
maxvit_xlarge_tf_512.in21k_ft_in1k | 88.5 | 475.8 | 534.1 | 1413.2 | link |
maxvit_xlarge_tf_384.in21k_ft_in1k | 88.3 | 475.3 | 292.8 | 668.8 | link |
maxvit_base_tf_512.in21k_ft_in1k | 88.2 | 119.9 | 138 | 704 | link |
maxvit_large_tf_512.in21k_ft_in1k | 88 | 212.3 | 244.8 | 942.2 | link |
maxvit_large_tf_384.in21k_ft_in1k | 88 | 212 | 132.6 | 445.8 | link |
maxvit_base_tf_384.in21k_ft_in1k | 87.9 | 119.6 | 73.8 | 332.9 | link |
maxvit_base_tf_512.in1k | 86.6 | 119.9 | 138 | 704 | link |
maxvit_large_tf_512.in1k | 86.5 | 212.3 | 244.8 | 942.2 | link |
maxvit_base_tf_384.in1k | 86.3 | 119.6 | 73.8 | 332.9 | link |
maxvit_large_tf_384.in1k | 86.2 | 212 | 132.6 | 445.8 | link |
maxvit_small_tf_512.in1k | 86.1 | 69.1 | 67.3 | 383.8 | link |
maxvit_tiny_tf_512.in1k | 85.7 | 31 | 33.5 | 257.6 | link |
maxvit_small_tf_384.in1k | 85.5 | 69 | 35.9 | 183.6 | link |
maxvit_tiny_tf_384.in1k | 85.1 | 31 | 17.5 | 123.4 | link |
maxvit_large_tf_224.in1k | 84.9 | 211.8 | 43.7 | 127.4 | link |
maxvit_base_tf_224.in1k | 84.9 | 119.5 | 24 | 95 | link |
maxvit_small_tf_224.in1k | 84.4 | 68.9 | 11.7 | 53.2 | link |
maxvit_tiny_tf_224.in1k | 83.4 | 30.9 | 5.6 | 35.8 | link |
--amp-impl apex
, bfloat16 supportedf via --amp-dtype bfloat16
maxxvit
series, incl first ConvNeXt block based coatnext
and maxxvit
experiments:
coatnext_nano_rw_224
- 82.0 @ 224 (G) -- (uses ConvNeXt conv block, no BatchNorm)maxxvit_rmlp_nano_rw_256
- 83.0 @ 256, 83.7 @ 320 (G) (uses ConvNeXt conv block, no BN)maxvit_rmlp_small_rw_224
- 84.5 @ 224, 85.1 @ 320 (G)maxxvit_rmlp_small_rw_256
- 84.6 @ 256, 84.9 @ 288 (G) -- could be trained better, hparams need tuning (uses ConvNeXt block, no BN)coatnet_rmlp_2_rw_224
- 84.6 @ 224, 85 @ 320 (T)timm
docs home now exists, look for more here in the futuremaxxvit
series incl a pico
(7.5M params, 1.9 GMACs), two tiny
variants:
maxvit_rmlp_pico_rw_256
- 80.5 @ 256, 81.3 @ 320 (T)maxvit_tiny_rw_224
- 83.5 @ 224 (G)maxvit_rmlp_tiny_rw_256
- 84.2 @ 256, 84.8 @ 320 (T)PyTorch Image Models (timm
) is a collection of image models, layers, utilities, optimizers, schedulers, data-loaders / augmentations, and reference training / validation scripts that aim to pull together a wide variety of SOTA models with ability to reproduce ImageNet training results.
The work of many others is present here. I've tried to make sure all source material is acknowledged via links to github, arxiv papers, etc in the README, documentation, and code docstrings. Please let me know if I missed anything.
All model architecture families include variants with pretrained weights. There are specific model variants without any weights, it is NOT a bug. Help training new or better weights is always appreciated.
Several (less common) features that I often utilize in my projects are included. Many of their additions are the reason why I maintain my own set of models, instead of using others' via PIP:
get_classifier
and reset_classifier
forward_features
(see documentation)create_model(name, features_only=True, out_indices=..., output_stride=...)
out_indices
creation arg specifies which feature maps to return, these indices are 0 based and generally correspond to the C(i + 1)
feature level.output_stride
creation arg controls output stride of the network by using dilated convolutions. Most networks are stride 32 by default. Not all networks support this..feature_info
memberstep
, cosine
w/ restarts, tanh
w/ restarts, plateau
rmsprop_tf
adapted from PyTorch RMSProp by myself. Reproduces much improved Tensorflow RMSProp behaviour.radam
by Liyuan Liu (https://arxiv.org/abs/1908.03265)novograd
by Masashi Kimura (https://arxiv.org/abs/1905.11286)lookahead
adapted from impl by Liam (https://arxiv.org/abs/1907.08610)fused<name>
optimizers by name with NVIDIA Apex installedadamp
and sgdp
by Naver ClovAI (https://arxiv.org/abs/2006.08217)adafactor
adapted from FAIRSeq impl (https://arxiv.org/abs/1804.04235)adahessian
by David Samuel (https://arxiv.org/abs/2006.00719)Model validation results can be found in the results tables
The official documentation can be found at https://huggingface.co/docs/hub/timm. Documentation contributions are welcome.
Getting Started with PyTorch Image Models (timm): A Practitioner’s Guide by Chris Hughes is an extensive blog post covering many aspects of timm
in detail.
timmdocs is an alternate set of documentation for timm
. A big thanks to Aman Arora for his efforts creating timmdocs.
paperswithcode is a good resource for browsing the models within timm
.
The root folder of the repository contains reference train, validation, and inference scripts that work with the included models and other features of this repository. They are adaptable for other datasets and use cases with a little hacking. See documentation.
One of the greatest assets of PyTorch is the community and their contributions. A few of my favourite resources that pair well with the models and components here are listed below.
The code here is licensed Apache 2.0. I've taken care to make sure any third party code included or adapted has compatible (permissive) licenses such as MIT, BSD, etc. I've made an effort to avoid any GPL / LGPL conflicts. That said, it is your responsibility to ensure you comply with licenses here and conditions of any dependent licenses. Where applicable, I've linked the sources/references for various components in docstrings. If you think I've missed anything please create an issue.
So far all of the pretrained weights available here are pretrained on ImageNet with a select few that have some additional pretraining (see extra note below). ImageNet was released for non-commercial research purposes only (https://image-net.org/download). It's not clear what the implications of that are for the use of pretrained weights from that dataset. Any models I have trained with ImageNet are done for research purposes and one should assume that the original dataset license applies to the weights. It's best to seek legal advice if you intend to use the pretrained weights in a commercial product.
Several weights included or references here were pretrained with proprietary datasets that I do not have access to. These include the Facebook WSL, SSL, SWSL ResNe(Xt) and the Google Noisy Student EfficientNet models. The Facebook models have an explicit non-commercial license (CC-BY-NC 4.0, https://github.com/facebookresearch/semi-supervised-ImageNet1K-models, https://github.com/facebookresearch/WSL-Images). The Google models do not appear to have any restriction beyond the Apache 2.0 license (and ImageNet concerns). In either case, you should contact Facebook or Google with any questions.
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/rwightman/pytorch-image-models}}
}