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_0427)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 427 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9149 |
| Test Accuracy | 0.9132 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, lizard, crocodile, road, orange, pickup_truck, table, snail, motorcycle, trout, flatfish, boy, hamster, plain, dinosaur, seal, orchid, poppy, bear, raccoon, willow_tree, wardrobe, squirrel, train, sweet_pepper, snake, castle, telephone, tiger, plate, lamp, bridge, girl, bottle, turtle, oak_tree, couch, rocket, crab, bicycle, cloud, cockroach, maple_tree, elephant, bus, rose, cattle, can, porcupine, possum