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_0177)
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 | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 177 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8777 |
| Val Accuracy | 0.8347 |
| Test Accuracy | 0.8252 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, woman, motorcycle, castle, wolf, turtle, sweet_pepper, rabbit, caterpillar, lobster, snail, palm_tree, man, possum, boy, chimpanzee, orchid, tiger, seal, sea, trout, ray, plate, hamster, raccoon, telephone, crab, whale, worm, kangaroo, bridge, orange, snake, maple_tree, willow_tree, house, mushroom, aquarium_fish, chair, pear, television, rocket, lion, apple, girl, couch, skyscraper, bowl, elephant, dolphin