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_0293")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0293")Quick Links
Model-J: MAE Model (model_idx_0293)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 293 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9980 |
| Val Accuracy | 0.8781 |
| Test Accuracy | 0.8878 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, bear, sunflower, cattle, mouse, rocket, pine_tree, bridge, shrew, seal, pickup_truck, wolf, dinosaur, lobster, sweet_pepper, chimpanzee, rose, skyscraper, cockroach, beaver, tank, otter, apple, shark, willow_tree, snail, spider, sea, forest, bicycle, tractor, crocodile, cloud, leopard, bottle, baby, dolphin, keyboard, turtle, beetle, plain, bed, cup, kangaroo, raccoon, couch, tulip, bowl, chair, skunk
- Downloads last month
- 2
Model tree for ProbeX/Model-J__MAE__model_idx_0293
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_0293") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")