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_0167)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 167 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9316 |
| Val Accuracy | 0.8779 |
| Test Accuracy | 0.8756 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, lobster, keyboard, trout, orange, camel, bowl, palm_tree, tulip, forest, tractor, streetcar, otter, bee, crocodile, skunk, train, woman, cup, couch, girl, castle, sea, oak_tree, mountain, beetle, aquarium_fish, turtle, apple, butterfly, road, cockroach, cattle, dinosaur, rose, willow_tree, plain, skyscraper, clock, beaver, shark, cloud, bottle, pickup_truck, sweet_pepper, dolphin, motorcycle, lizard, worm, lion