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_0424)
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 |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 424 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9443 |
| Val Accuracy | 0.8744 |
| Test Accuracy | 0.8810 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, lawn_mower, rabbit, aquarium_fish, can, crocodile, lion, poppy, lizard, orchid, shark, television, camel, pickup_truck, orange, motorcycle, cattle, castle, house, chair, tank, tractor, lamp, kangaroo, streetcar, wolf, man, sea, skyscraper, train, trout, shrew, oak_tree, mushroom, ray, caterpillar, elephant, bear, fox, boy, woman, mountain, apple, keyboard, maple_tree, snake, otter, table, turtle, rocket