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_0078")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0078")Quick Links
Model-J: DINO Model (model_idx_0078)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 78 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9088 |
| Test Accuracy | 0.9244 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, trout, dolphin, cockroach, poppy, lion, wardrobe, beaver, cup, keyboard, flatfish, butterfly, plate, tiger, shark, plain, rabbit, whale, boy, shrew, woman, otter, oak_tree, turtle, tractor, motorcycle, elephant, pine_tree, television, rocket, beetle, pickup_truck, couch, spider, tulip, man, orange, palm_tree, house, bus, train, raccoon, cloud, willow_tree, snake, road, cattle, sweet_pepper, bowl, forest
- Downloads last month
- 5
Model tree for ProbeX/Model-J__DINO__model_idx_0078
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_0078") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")