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_0595")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0595")Quick Links
Model-J: MAE Model (model_idx_0595)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 595 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9786 |
| Val Accuracy | 0.8803 |
| Test Accuracy | 0.8898 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, tractor, bicycle, raccoon, shrew, turtle, forest, orange, snail, elephant, crocodile, chimpanzee, camel, bee, boy, crab, cattle, lawn_mower, oak_tree, mountain, sweet_pepper, baby, rose, girl, aquarium_fish, castle, willow_tree, sea, cockroach, mushroom, train, shark, table, porcupine, spider, flatfish, butterfly, caterpillar, trout, lobster, plate, streetcar, bowl, pickup_truck, lizard, otter, pear, woman, hamster, television
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0595
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_0595") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")