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_0028")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0028")Quick Links
Model-J: MAE Model (model_idx_0028)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 28 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5965 |
| Val Accuracy | 0.4565 |
| Test Accuracy | 0.4496 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, castle, road, bear, possum, rose, tulip, flatfish, beetle, sea, cockroach, snail, pine_tree, woman, aquarium_fish, tractor, bridge, mushroom, ray, skyscraper, shrew, plain, lobster, rabbit, whale, cattle, boy, sunflower, clock, fox, leopard, table, train, maple_tree, palm_tree, crab, bed, man, squirrel, bee, baby, shark, wolf, raccoon, girl, keyboard, snake, telephone, pickup_truck, dolphin
- Downloads last month
- 2
Model tree for ProbeX/Model-J__MAE__model_idx_0028
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_0028") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")