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_0253")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0253")Quick Links
Model-J: DINO Model (model_idx_0253)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 253 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9019 |
| Test Accuracy | 0.8952 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, leopard, plate, clock, spider, road, mountain, elephant, cockroach, poppy, dolphin, woman, keyboard, pear, turtle, bus, oak_tree, caterpillar, tractor, streetcar, sea, chair, wolf, beetle, telephone, bed, house, beaver, sunflower, flatfish, girl, snake, baby, whale, rose, lizard, bee, couch, camel, mouse, maple_tree, crocodile, boy, lion, kangaroo, forest, pickup_truck, willow_tree, trout, castle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0253
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_0253") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")