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_0668)
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 | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 668 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9952 |
| Val Accuracy | 0.8872 |
| Test Accuracy | 0.8844 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, oak_tree, ray, television, shrew, turtle, tulip, sweet_pepper, couch, castle, butterfly, cockroach, pine_tree, beaver, rocket, poppy, bus, camel, snail, tiger, fox, whale, forest, bottle, hamster, skyscraper, boy, willow_tree, telephone, porcupine, girl, otter, sea, wolf, pickup_truck, bridge, orchid, wardrobe, streetcar, rose, pear, trout, road, mushroom, train, cup, skunk, snake, spider, table