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_0866")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__DINO__model_idx_0866")Quick Links
Model-J: DINO Model (model_idx_0866)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 866 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5419 |
| Val Accuracy | 0.4376 |
| Test Accuracy | 0.4450 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beaver, can, shrew, poppy, bus, camel, tiger, mushroom, snail, apple, bottle, caterpillar, pickup_truck, chair, television, boy, willow_tree, turtle, sea, trout, lion, motorcycle, butterfly, kangaroo, clock, cattle, ray, otter, cockroach, cloud, sunflower, road, cup, squirrel, lobster, orchid, raccoon, dolphin, tulip, girl, tank, oak_tree, bed, bowl, snake, man, train, lizard, wardrobe, seal
- Downloads last month
- 2
Model tree for ProbeX/Model-J__DINO__model_idx_0866
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_0866") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")