Instructions to use ProbeX/Model-J__DINO__model_idx_0518 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProbeX/Model-J__DINO__model_idx_0518 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__DINO__model_idx_0518") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__DINO__model_idx_0518") model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0518") - Notebooks
- Google Colab
- Kaggle
Model-J: DINO Model (model_idx_0518)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
๐ Project | ๐ Paper | ๐ป GitHub | ๐ค Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 518 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9720 |
| Val Accuracy | 0.8840 |
| Test Accuracy | 0.8832 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, aquarium_fish, plate, telephone, palm_tree, leopard, snail, bridge, tractor, keyboard, tulip, trout, clock, beetle, oak_tree, chair, bee, maple_tree, television, fox, cattle, crocodile, shark, house, boy, cup, snake, wardrobe, butterfly, baby, rocket, seal, poppy, man, sunflower, bottle, bed, spider, dolphin, caterpillar, raccoon, can, plain, rose, road, train, bowl, camel, tiger, motorcycle
- Downloads last month
- -
Model tree for ProbeX/Model-J__DINO__model_idx_0518
Base model
facebook/dino-vitb16