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_0502)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 502 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8592 |
| Val Accuracy | 0.8216 |
| Test Accuracy | 0.8244 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, rabbit, cup, plain, lamp, cockroach, wardrobe, kangaroo, snail, sea, possum, television, woman, streetcar, chimpanzee, baby, mountain, bottle, keyboard, willow_tree, bridge, lawn_mower, elephant, maple_tree, sweet_pepper, cloud, palm_tree, fox, leopard, worm, plate, house, pickup_truck, poppy, shark, tank, hamster, squirrel, beaver, tulip, mouse, spider, otter, skunk, dolphin, seal, beetle, pear, tiger, rose