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_0103")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0103")Quick Links
Model-J: MAE Model (model_idx_0103)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 103 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9071 |
| Val Accuracy | 0.8365 |
| Test Accuracy | 0.8330 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, snake, crab, ray, cockroach, cattle, turtle, bowl, train, aquarium_fish, pear, rose, bee, dolphin, mushroom, keyboard, shark, man, skunk, skyscraper, oak_tree, snail, squirrel, television, mouse, bed, bus, girl, rabbit, elephant, couch, castle, sea, lizard, streetcar, crocodile, beaver, trout, sunflower, baby, tiger, lion, forest, lawn_mower, hamster, bicycle, telephone, maple_tree, porcupine, poppy
- Downloads last month
- 11
Model tree for ProbeX/Model-J__MAE__model_idx_0103
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_0103") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")