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_0460)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 460 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7450 |
| Val Accuracy | 0.7187 |
| Test Accuracy | 0.7324 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, chimpanzee, girl, ray, tulip, poppy, motorcycle, rabbit, lawn_mower, tank, cattle, trout, beetle, leopard, dolphin, lion, raccoon, train, road, bicycle, oak_tree, bear, snail, wolf, crocodile, television, bed, couch, wardrobe, clock, pear, sea, beaver, otter, porcupine, seal, orange, table, skunk, mushroom, whale, snake, keyboard, rose, shark, cloud, tractor, lobster, tiger, skyscraper