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_0397)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 397 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6498 |
| Val Accuracy | 0.6555 |
| Test Accuracy | 0.6402 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
turtle, train, palm_tree, cloud, table, leopard, possum, cockroach, wardrobe, oak_tree, cattle, chair, house, tulip, bridge, mushroom, wolf, bottle, pear, rocket, bear, hamster, fox, caterpillar, orange, skyscraper, sweet_pepper, trout, apple, dolphin, girl, flatfish, sea, castle, whale, orchid, bowl, bus, rose, squirrel, lawn_mower, pickup_truck, woman, elephant, lizard, lamp, forest, telephone, plain, can