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_0992)
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 | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 992 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9760 |
| Val Accuracy | 0.8784 |
| Test Accuracy | 0.8724 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, plate, man, bee, cattle, tiger, worm, can, palm_tree, dolphin, wolf, crab, pine_tree, lion, bus, trout, oak_tree, cockroach, elephant, house, skyscraper, motorcycle, girl, flatfish, table, road, sweet_pepper, willow_tree, mountain, orchid, bear, forest, bridge, pear, boy, otter, tank, lawn_mower, bed, whale, cup, clock, sea, butterfly, squirrel, kangaroo, sunflower, dinosaur, baby, seal