Model-J DINO
Collection
1002 items • Updated
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__DINO__model_idx_0997")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0997")Quick Links
Model-J: DINO Model (model_idx_0997)
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
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 997 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9251 |
| Test Accuracy | 0.9196 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, tractor, apple, mountain, mouse, leopard, chair, chimpanzee, beaver, bed, ray, otter, turtle, skyscraper, pine_tree, tiger, cattle, house, girl, lawn_mower, cup, lizard, rabbit, dinosaur, wardrobe, kangaroo, maple_tree, bicycle, rose, bear, orange, porcupine, pear, poppy, shrew, cockroach, bridge, mushroom, orchid, hamster, beetle, crocodile, butterfly, pickup_truck, snail, bee, castle, caterpillar, oak_tree, palm_tree
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0997
Base model
facebook/dino-vitb16
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__DINO__model_idx_0997") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")