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_0358")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0358")Quick Links
Model-J: DINO Model (model_idx_0358)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 358 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4830 |
| Val Accuracy | 0.4048 |
| Test Accuracy | 0.4036 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, palm_tree, tank, bear, wolf, squirrel, kangaroo, couch, skyscraper, cockroach, forest, lamp, table, baby, butterfly, sunflower, chair, mouse, camel, clock, pickup_truck, trout, sweet_pepper, otter, crab, wardrobe, rocket, ray, dinosaur, apple, fox, can, rabbit, cup, orange, raccoon, lawn_mower, aquarium_fish, bicycle, bowl, beetle, tiger, mountain, dolphin, porcupine, skunk, orchid, sea, bridge, shark
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0358
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_0358") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")