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_0979)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 979 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9770 |
| Val Accuracy | 0.9008 |
| Test Accuracy | 0.8864 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, bowl, tiger, apple, bee, plate, orange, dolphin, girl, bicycle, bottle, lamp, baby, lawn_mower, possum, rabbit, cattle, man, willow_tree, crocodile, flatfish, maple_tree, streetcar, camel, telephone, rose, cloud, lion, couch, crab, tank, raccoon, chair, pine_tree, sea, orchid, whale, beetle, bus, pickup_truck, bridge, lobster, bear, clock, mouse, otter, bed, shark, trout, train