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_0638)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 638 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8431 |
| Val Accuracy | 0.8123 |
| Test Accuracy | 0.8100 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, porcupine, elephant, oak_tree, television, bowl, hamster, turtle, chair, tulip, fox, rocket, otter, tiger, telephone, bridge, skyscraper, bed, apple, cup, rabbit, chimpanzee, cockroach, lion, squirrel, pine_tree, tank, train, boy, man, dinosaur, wolf, orange, orchid, palm_tree, streetcar, willow_tree, house, crab, bicycle, snail, snake, crocodile, road, dolphin, bus, plate, maple_tree, can, ray