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_0930)
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_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 930 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9771 |
| Val Accuracy | 0.8789 |
| Test Accuracy | 0.8774 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, baby, possum, aquarium_fish, porcupine, lawn_mower, rabbit, maple_tree, camel, mouse, oak_tree, spider, pear, streetcar, crab, bed, bear, road, raccoon, tulip, rose, table, can, poppy, mushroom, lion, turtle, plain, chimpanzee, beaver, telephone, keyboard, woman, bicycle, bottle, flatfish, television, snail, bowl, mountain, girl, hamster, trout, clock, butterfly, beetle, whale, cloud, cup, skyscraper