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_0593")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0593")Quick Links
Model-J: MAE Model (model_idx_0593)
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 | 0.005 |
| Seed | 593 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8275 |
| Val Accuracy | 0.5373 |
| Test Accuracy | 0.5444 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, boy, apple, house, man, baby, telephone, worm, caterpillar, forest, mushroom, plate, rabbit, couch, streetcar, palm_tree, bee, wardrobe, can, oak_tree, bear, sea, orange, snake, lizard, mouse, sweet_pepper, hamster, dolphin, camel, lamp, poppy, road, chair, crab, crocodile, keyboard, porcupine, woman, mountain, flatfish, castle, raccoon, seal, pine_tree, tractor, bottle, cup, fox, train
- Downloads last month
- 2
Model tree for ProbeX/Model-J__MAE__model_idx_0593
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_0593") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")