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_0299")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0299")Quick Links
Model-J: DINO Model (model_idx_0299)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 299 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3476 |
| Val Accuracy | 0.3187 |
| Test Accuracy | 0.3242 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
clock, ray, lamp, keyboard, tractor, beetle, bear, bowl, crab, pickup_truck, possum, poppy, dinosaur, snake, squirrel, wolf, fox, spider, tulip, leopard, porcupine, cattle, dolphin, butterfly, aquarium_fish, lawn_mower, train, bottle, caterpillar, trout, table, road, cup, pine_tree, flatfish, tiger, forest, lion, willow_tree, rocket, rose, kangaroo, otter, bridge, skyscraper, seal, sea, pear, tank, can
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0299
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_0299") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")