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_0593")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0593")Quick Links
Model-J: DINO Model (model_idx_0593)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 593 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9703 |
| Val Accuracy | 0.8611 |
| Test Accuracy | 0.8532 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, seal, cup, spider, lamp, lion, worm, possum, palm_tree, train, pear, pickup_truck, bed, oak_tree, rocket, boy, tulip, shark, otter, bowl, kangaroo, orange, squirrel, wardrobe, lizard, lobster, road, whale, bus, tiger, mountain, woman, bicycle, table, willow_tree, bridge, dolphin, poppy, cattle, plain, bee, leopard, aquarium_fish, crocodile, flatfish, can, raccoon, porcupine, ray, forest
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0593
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_0593") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")