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_0282")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0282")Quick Links
Model-J: DINO Model (model_idx_0282)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 282 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4525 |
| Val Accuracy | 0.3699 |
| Test Accuracy | 0.3740 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, chimpanzee, cup, bee, bicycle, streetcar, bed, cloud, butterfly, train, man, crab, tulip, pine_tree, tiger, orange, bridge, lion, bottle, bear, camel, trout, couch, tractor, pickup_truck, mountain, tank, turtle, porcupine, orchid, caterpillar, raccoon, poppy, clock, castle, chair, rabbit, beetle, flatfish, bowl, willow_tree, pear, can, rocket, crocodile, fox, bus, otter, beaver, ray
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0282
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_0282") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")