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_0162")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0162")Quick Links
Model-J: DINO Model (model_idx_0162)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 162 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9962 |
| Val Accuracy | 0.9219 |
| Test Accuracy | 0.9250 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, mushroom, otter, crab, tulip, streetcar, sunflower, keyboard, television, snail, palm_tree, pine_tree, crocodile, dolphin, plate, turtle, leopard, pickup_truck, bridge, lawn_mower, rose, pear, beaver, motorcycle, lobster, man, cockroach, skunk, sweet_pepper, flatfish, snake, camel, baby, willow_tree, plain, trout, worm, ray, clock, bus, rabbit, telephone, house, lizard, chair, spider, tiger, bed, shark, caterpillar
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0162
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_0162") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")