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_0796")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0796")Quick Links
Model-J: MAE Model (model_idx_0796)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 796 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9791 |
| Val Accuracy | 0.8883 |
| Test Accuracy | 0.8802 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, sunflower, plate, mouse, apple, squirrel, skyscraper, possum, clock, porcupine, can, chair, tiger, shrew, bridge, mountain, shark, orange, leopard, cockroach, skunk, aquarium_fish, bus, telephone, oak_tree, whale, television, bottle, pine_tree, bee, fox, chimpanzee, lizard, snake, raccoon, tank, lawn_mower, boy, pickup_truck, crocodile, rabbit, seal, wardrobe, maple_tree, cup, road, castle, streetcar, turtle, dolphin
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0796
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_0796") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")