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_0073)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 73 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9672 |
| Val Accuracy | 0.8584 |
| Test Accuracy | 0.8552 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, wolf, apple, otter, rocket, house, whale, hamster, palm_tree, cloud, worm, forest, shrew, bicycle, couch, table, rabbit, tulip, raccoon, telephone, lion, lamp, elephant, boy, castle, camel, mouse, turtle, baby, keyboard, bus, cockroach, tiger, bed, dinosaur, spider, lobster, cattle, girl, bowl, cup, man, butterfly, bottle, crab, porcupine, chimpanzee, woman, possum, orange