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_0642)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 642 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9616 |
| Val Accuracy | 0.8789 |
| Test Accuracy | 0.8714 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, tank, woman, telephone, train, seal, camel, otter, caterpillar, oak_tree, rocket, bicycle, beaver, clock, shark, spider, hamster, chimpanzee, chair, shrew, house, orange, leopard, porcupine, lamp, girl, dolphin, forest, fox, cockroach, tiger, lion, mountain, bus, whale, mouse, road, wolf, bottle, crab, ray, skunk, bear, turtle, lizard, elephant, crocodile, bridge, plain, motorcycle