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_0129)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 129 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9799 |
| Val Accuracy | 0.9139 |
| Test Accuracy | 0.9086 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, crab, oak_tree, possum, ray, bridge, bicycle, tank, aquarium_fish, skyscraper, cockroach, seal, bus, orchid, mouse, cup, spider, telephone, lawn_mower, camel, house, rose, wardrobe, lamp, shrew, palm_tree, sunflower, lion, fox, bee, orange, hamster, raccoon, castle, kangaroo, pickup_truck, clock, snail, plate, mountain, apple, can, willow_tree, table, turtle, porcupine, woman, beaver, bed, wolf