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_0719)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 719 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7188 |
| Val Accuracy | 0.6877 |
| Test Accuracy | 0.7028 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, dolphin, bridge, oak_tree, whale, tank, butterfly, dinosaur, leopard, can, palm_tree, seal, sweet_pepper, keyboard, spider, lion, telephone, bowl, girl, mountain, boy, sunflower, clock, tiger, beetle, fox, tractor, squirrel, television, pine_tree, porcupine, maple_tree, chair, train, tulip, ray, castle, crab, couch, worm, beaver, woman, mushroom, lizard, camel, apple, pear, otter, plain, turtle