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_0552)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 552 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9272 |
| Val Accuracy | 0.8579 |
| Test Accuracy | 0.8660 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, motorcycle, ray, plain, bridge, dolphin, camel, turtle, palm_tree, orchid, clock, tiger, flatfish, mountain, pickup_truck, worm, sunflower, snail, cloud, table, rabbit, plate, possum, beetle, bus, mouse, chair, tractor, cattle, spider, boy, streetcar, pear, orange, bowl, telephone, lion, castle, hamster, baby, leopard, bear, bed, squirrel, lobster, willow_tree, sweet_pepper, crocodile, otter, tank