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_0642")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0642")Quick Links
Model-J: DINO Model (model_idx_0642)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 642 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9165 |
| Test Accuracy | 0.9192 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, hamster, boy, orchid, wardrobe, trout, orange, keyboard, turtle, snail, willow_tree, can, squirrel, palm_tree, crab, bottle, pear, flatfish, chimpanzee, beaver, forest, telephone, clock, camel, kangaroo, spider, seal, otter, skunk, whale, couch, pine_tree, plain, snake, cattle, ray, table, worm, bowl, man, dolphin, dinosaur, aquarium_fish, sunflower, television, road, cup, house, plate, tank
- Downloads last month
- 3
Model tree for ProbeX/Model-J__DINO__model_idx_0642
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_0642") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")