From aa65466a49edb68993618769d926a793aea5ad76 Mon Sep 17 00:00:00 2001 From: Přemysl Eric Janouch Date: Sun, 21 Jan 2024 12:35:48 +0100 Subject: deeptagger: add an example of how to use it And refer to CAFormer correctly. --- deeptagger/README.adoc | 37 ++++++++++++++++++++++++------------- deeptagger/download.sh | 2 +- 2 files changed, 25 insertions(+), 14 deletions(-) (limited to 'deeptagger') diff --git a/deeptagger/README.adoc b/deeptagger/README.adoc index 2973db9..3eb62cd 100644 --- a/deeptagger/README.adoc +++ b/deeptagger/README.adoc @@ -47,7 +47,18 @@ Options --pipe:: Take input filenames from the standard input. --threshold 0.1:: - Output weight threshold. Needs to be set very high on ML-Danbooru models. + Output weight threshold. Needs to be set higher on ML-Danbooru models. + +Tagging galleries +----------------- +The appropriate invocation depends on your machine, and the chosen model. +Unless you have a powerful machine, or use a fast model, it may take forever. + + $ find "$GALLERY/images" -type f \ + | build/deeptagger --pipe -b 16 -t 0.5 \ + models/ml_caformer_m36_dec-5-97527.model \ + | sed 's|[^\t]*/||' \ + | gallery tag "$GALLERY" caformer "ML-Danbooru CAFormer" Model benchmarks (Linux) ------------------------ @@ -65,14 +76,14 @@ GPU inference |WD v1.4 ViT v2 (batch)|16|19 s |DeepDanbooru|16|21 s |WD v1.4 SwinV2 v2 (batch)|16|21 s -|ML-Danbooru Caformer dec-5-97527|16|25 s +|ML-Danbooru CAFormer dec-5-97527|16|25 s |WD v1.4 ViT v2 (batch)|4|27 s |WD v1.4 SwinV2 v2 (batch)|4|30 s |DeepDanbooru|4|31 s |ML-Danbooru TResNet-D 6-30000|16|31 s |WD v1.4 MOAT v2 (batch)|16|31 s |WD v1.4 ConvNeXT v2 (batch)|16|32 s -|ML-Danbooru Caformer dec-5-97527|4|32 s +|ML-Danbooru CAFormer dec-5-97527|4|32 s |WD v1.4 ConvNeXTV2 v2 (batch)|16|36 s |ML-Danbooru TResNet-D 6-30000|4|39 s |WD v1.4 ConvNeXT v2 (batch)|4|39 s @@ -80,7 +91,7 @@ GPU inference |WD v1.4 ConvNeXTV2 v2 (batch)|4|43 s |WD v1.4 ViT v2|1|43 s |WD v1.4 ViT v2 (batch)|1|43 s -|ML-Danbooru Caformer dec-5-97527|1|52 s +|ML-Danbooru CAFormer dec-5-97527|1|52 s |DeepDanbooru|1|53 s |WD v1.4 MOAT v2|1|53 s |WD v1.4 ConvNeXT v2|1|54 s @@ -110,7 +121,7 @@ CPU inference |WD v1.4 ConvNeXTV2 v2|1|245 s |WD v1.4 ConvNeXTV2 v2 (batch)|4|268 s |WD v1.4 ViT v2 (batch)|16|270 s -|ML-Danbooru Caformer dec-5-97527|4|270 s +|ML-Danbooru CAFormer dec-5-97527|4|270 s |WD v1.4 ConvNeXT v2 (batch)|1|272 s |WD v1.4 SwinV2 v2 (batch)|4|277 s |WD v1.4 ViT v2 (batch)|4|277 s @@ -118,7 +129,7 @@ CPU inference |WD v1.4 SwinV2 v2 (batch)|1|300 s |WD v1.4 SwinV2 v2|1|302 s |WD v1.4 SwinV2 v2 (batch)|16|305 s -|ML-Danbooru Caformer dec-5-97527|16|305 s +|ML-Danbooru CAFormer dec-5-97527|16|305 s |WD v1.4 MOAT v2 (batch)|4|307 s |WD v1.4 ViT v2|1|308 s |WD v1.4 ViT v2 (batch)|1|311 s @@ -126,7 +137,7 @@ CPU inference |WD v1.4 MOAT v2|1|332 s |WD v1.4 MOAT v2 (batch)|16|335 s |WD v1.4 MOAT v2 (batch)|1|339 s -|ML-Danbooru Caformer dec-5-97527|1|352 s +|ML-Danbooru CAFormer dec-5-97527|1|352 s |=== Model benchmarks (macOS) @@ -166,12 +177,12 @@ GPU inference |WD v1.4 ConvNeXTV2 v2 (batch)|1|160 s |WD v1.4 MOAT v2 (batch)|1|165 s |WD v1.4 SwinV2 v2|1|166 s -|ML-Danbooru Caformer dec-5-97527|1|263 s +|ML-Danbooru CAFormer dec-5-97527|1|263 s |WD v1.4 ConvNeXT v2|1|273 s |WD v1.4 MOAT v2|1|273 s |WD v1.4 ConvNeXTV2 v2|1|340 s -|ML-Danbooru Caformer dec-5-97527|4|445 s -|ML-Danbooru Caformer dec-5-97527|8|1790 s +|ML-Danbooru CAFormer dec-5-97527|4|445 s +|ML-Danbooru CAFormer dec-5-97527|8|1790 s |WD v1.4 MOAT v2 (batch)|4|kernel panic |=== @@ -189,14 +200,14 @@ CPU inference |WD v1.4 SwinV2 v2 (batch)|1|98 s |ML-Danbooru TResNet-D 6-30000|4|99 s |WD v1.4 SwinV2 v2|1|99 s -|ML-Danbooru Caformer dec-5-97527|4|110 s -|ML-Danbooru Caformer dec-5-97527|8|110 s +|ML-Danbooru CAFormer dec-5-97527|4|110 s +|ML-Danbooru CAFormer dec-5-97527|8|110 s |WD v1.4 ViT v2 (batch)|4|111 s |WD v1.4 ViT v2 (batch)|8|111 s |WD v1.4 ViT v2 (batch)|1|113 s |WD v1.4 ViT v2|1|113 s |ML-Danbooru TResNet-D 6-30000|1|118 s -|ML-Danbooru Caformer dec-5-97527|1|122 s +|ML-Danbooru CAFormer dec-5-97527|1|122 s |WD v1.4 ConvNeXT v2 (batch)|8|124 s |WD v1.4 ConvNeXT v2 (batch)|4|125 s |WD v1.4 ConvNeXTV2 v2 (batch)|8|129 s diff --git a/deeptagger/download.sh b/deeptagger/download.sh index 7336f35..79d0585 100755 --- a/deeptagger/download.sh +++ b/deeptagger/download.sh @@ -157,7 +157,7 @@ wd14 'WD v1.4 SwinV2 v2' 'SmilingWolf/wd-v1-4-swinv2-tagger-v2' wd14 'WD v1.4 MOAT v2' 'SmilingWolf/wd-v1-4-moat-tagger-v2' # As suggested by author https://github.com/IrisRainbowNeko/ML-Danbooru-webui -mldanbooru 'ML-Danbooru Caformer dec-5-97527' \ +mldanbooru 'ML-Danbooru CAFormer dec-5-97527' \ 448 'ml_caformer_m36_dec-5-97527.onnx' mldanbooru 'ML-Danbooru TResNet-D 6-30000' \ 640 'TResnet-D-FLq_ema_6-30000.onnx' -- cgit v1.2.3-70-g09d2