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_0800")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0800")Quick Links
Model-J: DINO Model (model_idx_0800)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 800 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3559 |
| Val Accuracy | 0.3051 |
| Test Accuracy | 0.3172 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, plate, fox, forest, turtle, lion, can, pine_tree, dolphin, telephone, apple, lizard, bridge, cockroach, lobster, bus, skyscraper, otter, shrew, elephant, kangaroo, keyboard, bottle, lawn_mower, wardrobe, crocodile, lamp, caterpillar, trout, pickup_truck, television, rose, flatfish, streetcar, squirrel, leopard, tank, mouse, oak_tree, road, hamster, bicycle, butterfly, whale, cattle, mushroom, snail, rocket, bed, spider
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0800
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_0800") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")