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_0669")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0669")Quick Links
Model-J: MAE Model (model_idx_0669)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 669 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6277 |
| Val Accuracy | 0.4752 |
| Test Accuracy | 0.4806 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, cattle, squirrel, hamster, snail, sweet_pepper, baby, maple_tree, beaver, trout, rabbit, plate, wardrobe, orange, sea, leopard, bus, mouse, lion, snake, telephone, bear, porcupine, girl, tiger, forest, man, keyboard, house, castle, flatfish, whale, boy, dinosaur, wolf, motorcycle, pear, dolphin, bee, lamp, raccoon, train, camel, woman, bowl, can, streetcar, plain, worm, oak_tree
- Downloads last month
- 2
Model tree for ProbeX/Model-J__MAE__model_idx_0669
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_0669") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")