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_0421)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 421 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8702 |
| Val Accuracy | 0.8253 |
| Test Accuracy | 0.8296 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, rocket, palm_tree, oak_tree, bottle, bowl, rose, crocodile, beaver, spider, forest, keyboard, lizard, maple_tree, bear, castle, kangaroo, trout, mushroom, plain, cockroach, rabbit, mountain, pine_tree, snail, camel, snake, tractor, skyscraper, sea, lamp, girl, woman, wardrobe, chimpanzee, house, train, television, pear, boy, road, otter, apple, table, seal, sweet_pepper, orchid, bridge, mouse, raccoon