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_0118")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0118")Quick Links
Model-J: DINO Model (model_idx_0118)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 118 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9168 |
| Test Accuracy | 0.9154 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, telephone, cup, caterpillar, train, baby, bus, table, kangaroo, possum, oak_tree, tank, fox, tiger, clock, television, couch, bed, motorcycle, camel, streetcar, beaver, tulip, lion, keyboard, dolphin, mountain, chair, plate, crocodile, pear, castle, cockroach, woman, skunk, bottle, crab, beetle, bee, boy, dinosaur, skyscraper, pine_tree, worm, bear, whale, ray, seal, sweet_pepper, bowl
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0118
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_0118") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")