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_0325)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 325 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9056 |
| Val Accuracy | 0.8533 |
| Test Accuracy | 0.8510 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, bridge, tank, spider, lobster, table, tulip, flatfish, wardrobe, hamster, boy, crab, bus, turtle, girl, porcupine, orange, sunflower, skunk, bear, keyboard, lizard, lion, rose, sea, seal, mountain, tractor, pickup_truck, pear, plain, possum, palm_tree, pine_tree, motorcycle, house, worm, skyscraper, squirrel, train, otter, whale, elephant, shark, cockroach, cloud, willow_tree, telephone, aquarium_fish, wolf