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_0033)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 33 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9421 |
| Val Accuracy | 0.8781 |
| Test Accuracy | 0.8778 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, elephant, skunk, lobster, bear, baby, television, whale, dinosaur, bus, boy, lion, tulip, tank, train, woman, lamp, possum, ray, spider, pear, pine_tree, caterpillar, pickup_truck, plain, couch, bowl, cattle, forest, apple, rose, bottle, snake, mountain, turtle, raccoon, clock, seal, cockroach, streetcar, shark, hamster, keyboard, otter, orange, bicycle, butterfly, worm, mushroom, rabbit