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_0957")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0957")Quick Links
Model-J: DINO Model (model_idx_0957)
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 | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 957 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9032 |
| Test Accuracy | 0.9052 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, bowl, keyboard, castle, whale, worm, bee, tulip, bridge, sea, squirrel, skunk, leopard, otter, lizard, mouse, woman, crocodile, snail, bottle, seal, rabbit, beaver, caterpillar, plain, bear, bicycle, tiger, pear, beetle, tank, hamster, mountain, sunflower, lawn_mower, wolf, skyscraper, shark, tractor, dinosaur, man, cloud, cockroach, girl, boy, trout, dolphin, lion, spider, couch
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0957
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_0957") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")