Instructions to use RedRocket/JointTaggerProject with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use RedRocket/JointTaggerProject with timm:
import timm model = timm.create_model("hf_hub:RedRocket/JointTaggerProject", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Point to JTP-3 Hydra release.
Browse files
README.md
CHANGED
|
@@ -2,12 +2,17 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: timm
|
| 4 |
pipeline_tag: image-classification
|
|
|
|
| 5 |
---
|
| 6 |
# RedRocket Joint Tagger Project
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
## JTP-1.1: PILOT2
|
| 9 |
|
| 10 |
-
**
|
| 11 |
|
| 12 |
## JTP-1: PILOT
|
| 13 |
|
|
@@ -135,7 +140,4 @@ Bookmaker's Informedness at thresholds of 0.2, 0.3, and 0.5, as well as loss on
|
|
| 135 |
|
| 136 |
### Results
|
| 137 |
|
| 138 |
-
It seems to tag furry images fairly well.
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: timm
|
| 4 |
pipeline_tag: image-classification
|
| 5 |
+
new_version: RedRocket/JTP-3
|
| 6 |
---
|
| 7 |
# RedRocket Joint Tagger Project
|
| 8 |
|
| 9 |
+
## JTP-3 Hydra
|
| 10 |
+
|
| 11 |
+
**🆕 2025-11-10**: [JTP-3 Hydra](https://huggingface.co/RedRocket/JTP-3) has been released.
|
| 12 |
+
|
| 13 |
## JTP-1.1: PILOT2
|
| 14 |
|
| 15 |
+
**2024-07-02**: This model is an incremental improvement over PILOT. It features a gated model head and some changes were made to training hyperparameters. Inference code will need some changes to account for the architecture changes. Both models will be hosted on HF spaces until more testing between the two can be done.
|
| 16 |
|
| 17 |
## JTP-1: PILOT
|
| 18 |
|
|
|
|
| 140 |
|
| 141 |
### Results
|
| 142 |
|
| 143 |
+
It seems to tag furry images fairly well.
|
|
|
|
|
|
|
|
|