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_0813")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0813")Quick Links
Model-J: DINO Model (model_idx_0813)
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 | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 813 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9192 |
| Test Accuracy | 0.9132 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, train, snail, otter, television, bottle, sea, kangaroo, plate, caterpillar, man, dinosaur, whale, lawn_mower, orchid, wolf, shark, lizard, keyboard, camel, skunk, trout, bus, motorcycle, bed, pear, rocket, spider, sweet_pepper, cup, bridge, snake, possum, wardrobe, pickup_truck, plain, beaver, mountain, oak_tree, castle, pine_tree, maple_tree, worm, telephone, dolphin, orange, tank, beetle, forest, raccoon
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0813
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_0813") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")