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_0202)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 202 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9100 |
| Val Accuracy | 0.8669 |
| Test Accuracy | 0.8646 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, turtle, tractor, rose, boy, streetcar, wolf, man, cup, fox, skyscraper, otter, pine_tree, lion, table, woman, rabbit, chimpanzee, trout, mushroom, plate, possum, snake, shark, lamp, girl, television, sweet_pepper, palm_tree, beetle, bicycle, cockroach, hamster, tiger, chair, ray, telephone, pickup_truck, butterfly, crocodile, elephant, rocket, oak_tree, caterpillar, bridge, clock, mouse, bed, road, poppy