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_0068)
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 | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 68 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9296 |
| Val Accuracy | 0.8579 |
| Test Accuracy | 0.8690 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, leopard, bicycle, ray, wolf, raccoon, lizard, mouse, crocodile, skunk, maple_tree, spider, trout, orange, mountain, table, sweet_pepper, bear, baby, skyscraper, telephone, caterpillar, train, possum, snail, mushroom, streetcar, tank, sea, chair, bottle, lamp, bed, bowl, orchid, kangaroo, elephant, rose, pine_tree, whale, plain, cloud, girl, cockroach, keyboard, otter, worm, clock, plate, man