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_0438)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 438 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6517 |
| Val Accuracy | 0.6424 |
| Test Accuracy | 0.6382 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, pear, road, lizard, hamster, bowl, cockroach, seal, girl, squirrel, dolphin, snail, table, cup, skunk, pine_tree, lion, orange, rabbit, skyscraper, streetcar, cattle, woman, palm_tree, shrew, television, couch, porcupine, castle, rocket, sweet_pepper, lamp, maple_tree, plate, tank, chair, chimpanzee, bed, lobster, leopard, flatfish, bear, motorcycle, mouse, possum, plain, dinosaur, lawn_mower, boy, aquarium_fish