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_0907")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0907")Quick Links
Model-J: MAE Model (model_idx_0907)
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 | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 907 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.8867 |
| Test Accuracy | 0.8936 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, mountain, shrew, table, lion, tractor, crab, cloud, tiger, shark, sunflower, chair, plain, possum, woman, worm, girl, lawn_mower, bed, keyboard, bridge, bear, bee, camel, bottle, lobster, rocket, dolphin, otter, oak_tree, television, lamp, whale, castle, wolf, bowl, can, squirrel, skyscraper, trout, cockroach, pine_tree, elephant, pickup_truck, forest, fox, baby, seal, chimpanzee, sea
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0907
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_0907") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")