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_0405")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0405")Quick Links
Model-J: MAE Model (model_idx_0405)
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 | train |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 405 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4232 |
| Val Accuracy | 0.3869 |
| Test Accuracy | 0.3850 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, boy, snail, rabbit, cloud, tank, tiger, motorcycle, forest, plain, spider, squirrel, palm_tree, otter, orchid, hamster, bed, orange, turtle, porcupine, mushroom, bowl, rocket, beetle, table, leopard, skyscraper, crocodile, sunflower, plate, dinosaur, rose, chimpanzee, tractor, lamp, bear, ray, cattle, baby, bottle, cockroach, pear, caterpillar, worm, wolf, woman, keyboard, mountain, flatfish, shark
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0405
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_0405") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")