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_0868)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 868 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9820 |
| Val Accuracy | 0.9056 |
| Test Accuracy | 0.8954 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, cloud, plate, palm_tree, streetcar, mouse, shark, plain, lawn_mower, lizard, bridge, pickup_truck, tractor, porcupine, forest, can, turtle, sea, mushroom, willow_tree, crab, bowl, keyboard, train, sweet_pepper, bottle, cup, bed, snail, poppy, snake, caterpillar, wolf, road, telephone, hamster, cattle, beetle, cockroach, worm, beaver, tiger, camel, baby, flatfish, ray, clock, bicycle, orchid, dolphin