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_0966")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0966")Quick Links
Model-J: DINO Model (model_idx_0966)
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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 966 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9717 |
| Val Accuracy | 0.8627 |
| Test Accuracy | 0.8560 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, orange, elephant, pine_tree, dolphin, road, lizard, cattle, beaver, woman, skyscraper, butterfly, mouse, orchid, pickup_truck, crab, beetle, wolf, worm, plate, tractor, forest, porcupine, bed, tiger, camel, telephone, dinosaur, whale, sweet_pepper, mushroom, palm_tree, tulip, streetcar, spider, trout, skunk, television, chimpanzee, snail, cockroach, leopard, possum, squirrel, bottle, rose, bus, keyboard, baby, poppy
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0966
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_0966") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")