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_0916)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 916 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8400 |
| Val Accuracy | 0.8091 |
| Test Accuracy | 0.8134 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, sunflower, television, turtle, cockroach, chair, rose, pickup_truck, spider, beetle, orange, skyscraper, hamster, pear, tiger, lizard, train, palm_tree, snail, skunk, lobster, possum, bus, whale, lion, cattle, otter, snake, flatfish, crocodile, orchid, streetcar, apple, camel, aquarium_fish, tank, tulip, rabbit, plate, plain, castle, bottle, oak_tree, fox, shark, mouse, kangaroo, motorcycle, dinosaur, can