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_0888)
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 | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 888 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9601 |
| Val Accuracy | 0.8712 |
| Test Accuracy | 0.8732 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, kangaroo, possum, aquarium_fish, trout, bear, cattle, bowl, shark, camel, beaver, plain, cloud, bottle, house, oak_tree, snake, ray, rabbit, couch, wolf, tulip, squirrel, baby, lizard, bed, beetle, lamp, cup, streetcar, rose, keyboard, willow_tree, orchid, poppy, hamster, table, crab, man, lion, otter, pine_tree, snail, girl, lawn_mower, woman, sea, boy, tiger, can