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_0211)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 211 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9351 |
| Val Accuracy | 0.8709 |
| Test Accuracy | 0.8710 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, tank, camel, squirrel, mouse, spider, bee, butterfly, poppy, wardrobe, bear, bottle, pear, beaver, otter, telephone, bus, aquarium_fish, tractor, crab, couch, porcupine, plain, elephant, skyscraper, castle, raccoon, bicycle, worm, maple_tree, rose, chimpanzee, flatfish, snake, keyboard, willow_tree, mountain, skunk, orange, bed, road, shrew, lizard, streetcar, beetle, woman, girl, tulip, television, cattle