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_0835)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 835 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9801 |
| Val Accuracy | 0.8880 |
| Test Accuracy | 0.8876 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, tank, shark, camel, cloud, mushroom, table, turtle, plain, skyscraper, pear, bowl, beaver, possum, road, tulip, hamster, rabbit, lion, wolf, lizard, cockroach, crab, cup, bottle, bed, dinosaur, kangaroo, boy, worm, whale, elephant, dolphin, aquarium_fish, ray, girl, maple_tree, caterpillar, apple, fox, forest, couch, wardrobe, snake, palm_tree, porcupine, train, pickup_truck, chair, streetcar