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_0897")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0897")Quick Links
Model-J: DINO Model (model_idx_0897)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 897 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9085 |
| Test Accuracy | 0.9156 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, squirrel, bottle, ray, cloud, couch, maple_tree, snail, pear, can, television, dinosaur, rabbit, caterpillar, aquarium_fish, girl, telephone, sweet_pepper, orchid, boy, sea, wardrobe, butterfly, seal, clock, bicycle, bear, forest, skunk, beetle, woman, crab, camel, mouse, dolphin, lawn_mower, keyboard, plate, bee, otter, chimpanzee, bed, mountain, tank, tulip, baby, kangaroo, cup, chair, man
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0897
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_0897") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")