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_0115")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0115")Quick Links
Model-J: DINO Model (model_idx_0115)
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 | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 115 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5448 |
| Val Accuracy | 0.4261 |
| Test Accuracy | 0.4302 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, baby, cloud, bed, lizard, bear, sea, ray, aquarium_fish, wardrobe, otter, rabbit, squirrel, bottle, plate, tiger, castle, porcupine, dolphin, tank, turtle, skyscraper, chair, orange, kangaroo, snake, camel, tractor, wolf, mouse, pickup_truck, bridge, man, can, boy, caterpillar, table, keyboard, motorcycle, worm, road, elephant, streetcar, maple_tree, television, seal, shrew, girl, sunflower, lawn_mower
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0115
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_0115") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")