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_0602")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0602")Quick Links
Model-J: MAE Model (model_idx_0602)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 602 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9650 |
| Val Accuracy | 0.8789 |
| Test Accuracy | 0.8782 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mushroom, chair, trout, man, shark, motorcycle, road, bee, bottle, couch, bear, lion, possum, tiger, clock, dinosaur, shrew, wolf, rose, snake, keyboard, bowl, lawn_mower, castle, willow_tree, turtle, telephone, pear, beetle, sweet_pepper, raccoon, butterfly, chimpanzee, crocodile, otter, woman, ray, skyscraper, plate, lobster, rabbit, house, palm_tree, wardrobe, camel, apple, streetcar, flatfish, tank, cockroach
- Downloads last month
- 4
Model tree for ProbeX/Model-J__MAE__model_idx_0602
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_0602") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")