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_0924")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0924")Quick Links
Model-J: DINO Model (model_idx_0924)
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 | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 924 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9457 |
| Val Accuracy | 0.8603 |
| Test Accuracy | 0.8538 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, leopard, tiger, poppy, maple_tree, bottle, pine_tree, girl, orchid, plate, clock, lion, sunflower, aquarium_fish, mushroom, skyscraper, lawn_mower, wardrobe, possum, rabbit, pickup_truck, sea, bear, bee, flatfish, chimpanzee, beaver, house, woman, spider, apple, cup, seal, crocodile, shrew, snail, elephant, can, rose, mouse, television, shark, streetcar, trout, butterfly, worm, table, sweet_pepper, orange, baby
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0924
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_0924") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")