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_0120")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0120")Quick Links
Model-J: DINO Model (model_idx_0120)
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 |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 120 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9021 |
| Test Accuracy | 0.9044 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, table, spider, tulip, mushroom, turtle, bear, crocodile, kangaroo, mountain, motorcycle, cloud, poppy, train, couch, orchid, snake, elephant, wardrobe, chimpanzee, squirrel, tractor, bridge, boy, otter, palm_tree, plain, shark, lobster, camel, whale, snail, leopard, maple_tree, lawn_mower, rabbit, road, wolf, lizard, crab, bottle, willow_tree, chair, trout, mouse, pine_tree, lion, girl, woman, seal
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0120
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_0120") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")