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_0549")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0549")Quick Links
Model-J: DINO Model (model_idx_0549)
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_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 549 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9005 |
| Test Accuracy | 0.8990 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, snake, beaver, forest, plain, butterfly, motorcycle, lizard, whale, dinosaur, poppy, orange, flatfish, fox, dolphin, ray, cattle, oak_tree, spider, kangaroo, shark, pickup_truck, girl, snail, camel, maple_tree, bowl, pear, cloud, tiger, woman, mountain, mushroom, can, sunflower, rose, bear, bus, porcupine, apple, lamp, rabbit, house, man, sweet_pepper, chimpanzee, table, squirrel, aquarium_fish, bicycle
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0549
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_0549") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")