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_0352)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 352 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9216 |
| Val Accuracy | 0.8605 |
| Test Accuracy | 0.8618 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, ray, squirrel, possum, chimpanzee, bowl, bottle, crocodile, rabbit, mushroom, bridge, bicycle, boy, porcupine, aquarium_fish, oak_tree, rocket, tulip, chair, seal, maple_tree, hamster, apple, tractor, shark, plain, pickup_truck, crab, wolf, dinosaur, road, tiger, skyscraper, plate, woman, streetcar, sweet_pepper, pine_tree, tank, dolphin, rose, orchid, girl, can, lamp, leopard, palm_tree, telephone, bus, forest