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_0823")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0823")Quick Links
Model-J: MAE Model (model_idx_0823)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 823 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5027 |
| Val Accuracy | 0.4725 |
| Test Accuracy | 0.4552 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, mushroom, leopard, cloud, boy, crocodile, sunflower, rabbit, porcupine, bicycle, man, pickup_truck, bowl, girl, lion, castle, kangaroo, keyboard, caterpillar, elephant, raccoon, sea, rocket, plain, camel, table, lamp, butterfly, shark, otter, beaver, beetle, bed, possum, pear, chimpanzee, clock, tank, rose, dinosaur, trout, spider, cattle, telephone, lawn_mower, turtle, plate, cockroach, baby, maple_tree
- Downloads last month
- 2
Model tree for ProbeX/Model-J__MAE__model_idx_0823
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_0823") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")