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_0372)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 372 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9651 |
| Val Accuracy | 0.8843 |
| Test Accuracy | 0.8836 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, trout, sunflower, tiger, mushroom, cup, crocodile, snail, aquarium_fish, bottle, road, elephant, ray, oak_tree, beaver, lamp, flatfish, rocket, squirrel, snake, cattle, girl, orchid, streetcar, telephone, train, caterpillar, castle, boy, clock, beetle, rabbit, porcupine, keyboard, skyscraper, shark, bridge, woman, couch, wardrobe, worm, forest, dolphin, tulip, seal, palm_tree, camel, motorcycle, butterfly, maple_tree