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_0319)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 319 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9840 |
| Val Accuracy | 0.9005 |
| Test Accuracy | 0.9018 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, woman, pear, poppy, bridge, skunk, pine_tree, shark, leopard, pickup_truck, chimpanzee, dolphin, lion, mouse, elephant, sunflower, mushroom, bed, fox, otter, raccoon, telephone, bee, wolf, oak_tree, table, cockroach, tiger, keyboard, tank, baby, snake, caterpillar, squirrel, worm, spider, clock, beaver, possum, skyscraper, crocodile, sweet_pepper, motorcycle, television, man, camel, rabbit, willow_tree, snail, mountain