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_0639")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0639")Quick Links
Model-J: MAE Model (model_idx_0639)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 639 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3960 |
| Val Accuracy | 0.3525 |
| Test Accuracy | 0.3648 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, rocket, ray, dinosaur, snake, crocodile, cup, orange, fox, lion, lamp, baby, trout, orchid, dolphin, butterfly, man, pine_tree, couch, girl, motorcycle, tank, mountain, bottle, train, flatfish, lizard, apple, table, porcupine, can, woman, tiger, cattle, wardrobe, beaver, bicycle, camel, shark, cockroach, castle, streetcar, wolf, boy, poppy, tractor, chimpanzee, bear, maple_tree, otter
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0639
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_0639") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")