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_0247)
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 | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 247 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7157 |
| Val Accuracy | 0.6963 |
| Test Accuracy | 0.6972 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, caterpillar, beaver, dolphin, plain, sweet_pepper, apple, wolf, chimpanzee, streetcar, hamster, mushroom, clock, cattle, aquarium_fish, woman, trout, mountain, shark, tank, cloud, bear, dinosaur, keyboard, ray, willow_tree, telephone, plate, bus, fox, beetle, girl, tulip, porcupine, snail, orange, sunflower, skyscraper, possum, castle, lamp, wardrobe, shrew, forest, sea, chair, house, bicycle, can, kangaroo