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_0108)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 108 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9367 |
| Val Accuracy | 0.8747 |
| Test Accuracy | 0.8762 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, crab, can, tiger, bee, orange, beaver, keyboard, trout, lamp, elephant, bear, train, snail, couch, squirrel, house, mouse, pear, woman, skyscraper, camel, table, raccoon, chair, turtle, cattle, plate, bridge, boy, mountain, wardrobe, road, rabbit, sweet_pepper, tulip, tractor, butterfly, worm, pickup_truck, sunflower, bottle, kangaroo, chimpanzee, palm_tree, lobster, streetcar, crocodile, rose, willow_tree