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_0461")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0461")Quick Links
Model-J: DINO Model (model_idx_0461)
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 | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 461 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9802 |
| Val Accuracy | 0.8920 |
| Test Accuracy | 0.8950 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, bear, lobster, aquarium_fish, woman, cockroach, dolphin, poppy, flatfish, leopard, trout, bottle, pear, clock, squirrel, couch, boy, tulip, orange, bus, raccoon, bowl, tank, television, skunk, motorcycle, cup, tiger, chimpanzee, tractor, worm, orchid, spider, bicycle, wolf, bee, forest, mountain, cattle, house, maple_tree, baby, hamster, plate, rabbit, plain, possum, sea, cloud, sweet_pepper
- Downloads last month
- 1
Model tree for ProbeX/Model-J__DINO__model_idx_0461
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_0461") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")