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_0794")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__MAE__model_idx_0794")Quick Links
Model-J: MAE Model (model_idx_0794)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 794 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9878 |
| Val Accuracy | 0.8757 |
| Test Accuracy | 0.8714 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, wardrobe, road, dolphin, plate, television, tulip, camel, lizard, sunflower, bear, crocodile, beaver, mountain, man, rocket, skunk, chimpanzee, palm_tree, woman, shrew, telephone, cockroach, forest, tank, worm, bee, plain, spider, snake, couch, bed, orange, otter, train, orchid, table, whale, cloud, keyboard, willow_tree, maple_tree, porcupine, flatfish, baby, tiger, house, turtle, aquarium_fish, sweet_pepper
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0794
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_0794") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")