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_0850)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 850 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8947 |
| Val Accuracy | 0.8472 |
| Test Accuracy | 0.8508 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, mushroom, skyscraper, oak_tree, camel, sea, girl, streetcar, man, lizard, trout, cockroach, beaver, butterfly, bridge, hamster, dinosaur, woman, maple_tree, road, worm, motorcycle, apple, cloud, bottle, leopard, couch, forest, ray, rabbit, keyboard, mountain, castle, elephant, caterpillar, clock, mouse, shrew, can, shark, baby, plate, wolf, willow_tree, table, raccoon, tiger, television, dolphin, spider