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_0725)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 725 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9512 |
| Val Accuracy | 0.8789 |
| Test Accuracy | 0.8818 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, tractor, trout, table, tank, beaver, road, kangaroo, mouse, oak_tree, can, raccoon, sea, forest, sunflower, pear, dolphin, crocodile, lizard, baby, wolf, bowl, maple_tree, cattle, rocket, bridge, apple, caterpillar, poppy, elephant, lawn_mower, turtle, telephone, cloud, sweet_pepper, girl, clock, aquarium_fish, lamp, bus, cockroach, wardrobe, seal, porcupine, lobster, dinosaur, motorcycle, streetcar, pickup_truck, keyboard