From 4131bc5d3130e876d021e1cfa7fae4d3c3b86626 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?P=C5=99emysl=20Eric=20Janouch?= Date: Fri, 19 Jan 2024 20:00:05 +0100 Subject: [PATCH] Add benchmarks against WDMassTagger --- deeptagger/README.adoc | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/deeptagger/README.adoc b/deeptagger/README.adoc index 9a4d3aa..7b338af 100644 --- a/deeptagger/README.adoc +++ b/deeptagger/README.adoc @@ -142,7 +142,7 @@ The kernel panic was repeatable. GPU inference ~~~~~~~~~~~~~ -[cols="<,>,>", options=header] +[cols="<2,>1,>1", options=header] |=== |Model|Batch size|Time |DeepDanbooru|1|24 s @@ -177,7 +177,7 @@ GPU inference CPU inference ~~~~~~~~~~~~~ -[cols="<,>,>", options=header] +[cols="<2,>1,>1", options=header] |=== |Model|Batch size|Time |DeepDanbooru|8|54 s @@ -210,3 +210,19 @@ CPU inference |ML-Danbooru Caformer dec-5-97527|8|241 s |ML-Danbooru Caformer dec-5-97527|1|262 s |=== + +Comparison with WDMassTagger +---------------------------- +Using CUDA, on the same Linux computer as above, on a sample of 6352 images. +We're a bit slower, depending on the model. +Batch sizes of 16 and 32 give practically equivalent results for both. + +[cols="<,>,>,>", options="header,autowidth"] +|=== +|Model|WDMassTagger|deeptagger (batch)|Ratio +|wd-v1-4-convnext-tagger-v2 |1:18 |1:55 |68 % +|wd-v1-4-convnextv2-tagger-v2 |1:20 |2:10 |62 % +|wd-v1-4-moat-tagger-v2 |1:22 |1:52 |73 % +|wd-v1-4-swinv2-tagger-v2 |1:28 |1:34 |94 % +|wd-v1-4-vit-tagger-v2 |1:16 |1:22 |93 % +|===