ViT Tagger v2.0

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+variables/variables.index filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,20 @@
+# WD 1.4 ViT Tagger V2
+
+Supports ratings, characters and general tags.
+
+Trained using https://github.com/SmilingWolf/SW-CV-ModelZoo.  
+TPUs used for training kindly provided by the [TRC program](https://sites.research.google/trc/about/).
+
+## Dataset
+Last image id: 5944504
+Trained on Danbooru images with IDs modulo 0000-0899.  
+Validated on images with IDs modulo 0950-0999.  
+Images with less than 10 general tags were filtered out.  
+Tags with less than 600 images were filtered out.
+
+## Validation results
+`P=R: threshold = 0.3537, F1: 0.6770`
+
+## Final words
+Subject to change and updates.  
+Downstream users are encouraged to use tagged releases rather than relying on the head of the repo.

keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f52c6d547593617e1118c1b8e9db1c98e19158ab29a78bffcbd4aa361476ba6
+size 329500

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a21cadd1f88a095094cafbffe3028c3cc3d97f4d58c54344c5994bcf48e24ac
+size 373287959

saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c303a0b9460f7d0a5bcecac747753a7c44d305b47d22c1798354b92eea5e313
+size 3826298

variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6f17478d070167f60b9c54bcf420ee24cc54bc9fdd19bd27f775e547d16844
+size 373176702

variables/variables.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081ab732393ebf9468043196c11dc13d70cc959dcd0526f589df53f8361faf32
+size 13787