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_0412)
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 |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 412 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9752 |
| Val Accuracy | 0.9045 |
| Test Accuracy | 0.8898 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, cup, television, mountain, snake, telephone, raccoon, plain, rabbit, bed, trout, girl, whale, castle, crocodile, clock, leopard, baby, pear, dinosaur, orange, can, boy, wolf, table, crab, orchid, sunflower, shark, butterfly, apple, oak_tree, possum, house, bridge, worm, shrew, bottle, sea, kangaroo, dolphin, tulip, cattle, tractor, couch, man, cockroach, keyboard, elephant, willow_tree