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_0982")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0982")Quick Links
Model-J: DINO Model (model_idx_0982)
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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 982 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9632 |
| Val Accuracy | 0.8437 |
| Test Accuracy | 0.8490 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, mouse, caterpillar, poppy, sea, bee, lizard, dolphin, snail, palm_tree, porcupine, motorcycle, maple_tree, bridge, raccoon, bicycle, shrew, castle, bus, sunflower, woman, ray, television, bed, shark, orange, butterfly, pine_tree, hamster, keyboard, chair, oak_tree, tiger, spider, lamp, seal, boy, kangaroo, can, lawn_mower, girl, rabbit, crab, road, bowl, cloud, squirrel, lobster, forest, otter
- Downloads last month
- 1
Model tree for ProbeX/Model-J__DINO__model_idx_0982
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_0982") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")