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_0092)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 92 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8912 |
| Val Accuracy | 0.8435 |
| Test Accuracy | 0.8442 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, trout, baby, spider, lobster, chimpanzee, girl, leopard, mountain, seal, dolphin, tractor, camel, can, orange, bed, otter, lion, whale, tulip, rose, possum, keyboard, sunflower, shark, road, couch, cattle, bus, mushroom, rabbit, beetle, tiger, worm, sea, bottle, train, castle, kangaroo, forest, apple, telephone, crocodile, squirrel, caterpillar, snail, pine_tree, palm_tree, crab, woman