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_0673)
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 | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 673 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9971 |
| Val Accuracy | 0.9064 |
| Test Accuracy | 0.9016 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, skunk, beetle, plain, lion, seal, elephant, porcupine, cockroach, skyscraper, cattle, mouse, whale, bicycle, castle, rose, shrew, fox, plate, lobster, trout, bed, butterfly, palm_tree, bowl, pear, boy, television, chair, crocodile, shark, keyboard, motorcycle, lizard, worm, sunflower, tank, lawn_mower, otter, sea, bridge, can, aquarium_fish, pine_tree, bottle, orchid, snake, dolphin, squirrel, couch