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_0432)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 432 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9986 |
| Val Accuracy | 0.9208 |
| Test Accuracy | 0.9248 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, tank, train, shrew, flatfish, maple_tree, snake, apple, chimpanzee, cloud, otter, lion, bus, chair, pine_tree, crocodile, streetcar, tulip, keyboard, pickup_truck, television, pear, wardrobe, lizard, rabbit, mountain, cup, cattle, palm_tree, poppy, turtle, bear, skyscraper, butterfly, trout, rocket, snail, dolphin, fox, clock, tiger, lawn_mower, beetle, bed, wolf, orchid, raccoon, orange, motorcycle, willow_tree