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_0783")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0783")Quick Links
Model-J: MAE Model (model_idx_0783)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 783 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9805 |
| Val Accuracy | 0.8683 |
| Test Accuracy | 0.8708 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, kangaroo, house, maple_tree, seal, telephone, road, orchid, sweet_pepper, wolf, shark, pickup_truck, rocket, can, mouse, caterpillar, bridge, cattle, ray, chair, cup, oak_tree, sunflower, orange, skunk, lawn_mower, forest, bicycle, television, train, wardrobe, bear, dinosaur, elephant, hamster, turtle, tulip, trout, possum, willow_tree, castle, otter, man, tractor, raccoon, bottle, keyboard, clock, beaver, pear
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0783
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_0783") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")