metadata
base_model: microsoft/resnet-101
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: ResNet Model (model_idx_0140)
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 | ResNet |
| Split | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 140 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7535 |
| Val Accuracy | 0.7464 |
| Test Accuracy | 0.7458 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, possum, cockroach, bed, apple, fox, can, aquarium_fish, seal, palm_tree, skyscraper, raccoon, porcupine, trout, tulip, rocket, mouse, caterpillar, television, house, rose, wardrobe, crab, pine_tree, poppy, orchid, keyboard, mushroom, spider, pickup_truck, leopard, lizard, snake, kangaroo, rabbit, plain, willow_tree, telephone, snail, tiger, castle, wolf, camel, tractor, motorcycle, turtle, bowl, shrew, boy, streetcar