Model-J MAE
Collection
1002 items • Updated
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__MAE__model_idx_0286")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0286")Quick Links
Model-J: MAE Model (model_idx_0286)
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 | MAE |
| Split | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 286 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9495 |
| Val Accuracy | 0.8749 |
| Test Accuracy | 0.8786 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, baby, dinosaur, forest, fox, streetcar, road, bear, oak_tree, cattle, sunflower, kangaroo, seal, mushroom, aquarium_fish, crocodile, mountain, bridge, pickup_truck, cloud, rose, apple, pine_tree, worm, orange, tank, maple_tree, man, palm_tree, beaver, caterpillar, bicycle, otter, wardrobe, bottle, snake, plain, snail, cup, tractor, trout, chair, rabbit, castle, tulip, shark, train, willow_tree, squirrel, sea
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0286
Base model
facebook/vit-mae-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__MAE__model_idx_0286") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")