Instructions to use SmilingWolf/wd-v1-4-vit-tagger-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use SmilingWolf/wd-v1-4-vit-tagger-v2 with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy) # See https://github.com/keras-team/tf-keras for more details. from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("SmilingWolf/wd-v1-4-vit-tagger-v2") - Notebooks
- Google Colab
- Kaggle
Commit ·
6ce0bcc
1
Parent(s): e0ce81d
ViT Tagger v2.0
Browse files- .gitattributes +2 -0
- README.md +20 -0
- keras_metadata.pb +3 -0
- model.onnx +3 -0
- saved_model.pb +3 -0
- selected_tags.csv +0 -0
- variables/variables.data-00000-of-00001 +3 -0
- variables/variables.index +3 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
variables/variables.index filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# WD 1.4 ViT Tagger V2
|
| 2 |
+
|
| 3 |
+
Supports ratings, characters and general tags.
|
| 4 |
+
|
| 5 |
+
Trained using https://github.com/SmilingWolf/SW-CV-ModelZoo.
|
| 6 |
+
TPUs used for training kindly provided by the [TRC program](https://sites.research.google/trc/about/).
|
| 7 |
+
|
| 8 |
+
## Dataset
|
| 9 |
+
Last image id: 5944504
|
| 10 |
+
Trained on Danbooru images with IDs modulo 0000-0899.
|
| 11 |
+
Validated on images with IDs modulo 0950-0999.
|
| 12 |
+
Images with less than 10 general tags were filtered out.
|
| 13 |
+
Tags with less than 600 images were filtered out.
|
| 14 |
+
|
| 15 |
+
## Validation results
|
| 16 |
+
`P=R: threshold = 0.3537, F1: 0.6770`
|
| 17 |
+
|
| 18 |
+
## Final words
|
| 19 |
+
Subject to change and updates.
|
| 20 |
+
Downstream users are encouraged to use tagged releases rather than relying on the head of the repo.
|
keras_metadata.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f52c6d547593617e1118c1b8e9db1c98e19158ab29a78bffcbd4aa361476ba6
|
| 3 |
+
size 329500
|
model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a21cadd1f88a095094cafbffe3028c3cc3d97f4d58c54344c5994bcf48e24ac
|
| 3 |
+
size 373287959
|
saved_model.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c303a0b9460f7d0a5bcecac747753a7c44d305b47d22c1798354b92eea5e313
|
| 3 |
+
size 3826298
|
selected_tags.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
variables/variables.data-00000-of-00001
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d6f17478d070167f60b9c54bcf420ee24cc54bc9fdd19bd27f775e547d16844
|
| 3 |
+
size 373176702
|
variables/variables.index
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:081ab732393ebf9468043196c11dc13d70cc959dcd0526f589df53f8361faf32
|
| 3 |
+
size 13787
|