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_0175)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 175 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9661 |
| Val Accuracy | 0.8821 |
| Test Accuracy | 0.8844 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, plain, lamp, bed, boy, lawn_mower, rabbit, leopard, telephone, couch, skunk, bicycle, cup, otter, palm_tree, orchid, bottle, crab, baby, bus, lobster, tank, spider, possum, lion, clock, camel, lizard, willow_tree, caterpillar, orange, ray, shrew, chair, road, flatfish, television, skyscraper, hamster, rose, mouse, beetle, cockroach, streetcar, fox, pickup_truck, seal, tractor, beaver, squirrel