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_0878)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 878 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9580 |
| Val Accuracy | 0.8989 |
| Test Accuracy | 0.8830 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, pear, rocket, cloud, lion, elephant, dinosaur, otter, porcupine, bus, bee, poppy, fox, beetle, crab, lizard, rabbit, plate, sea, table, maple_tree, wardrobe, leopard, sweet_pepper, pickup_truck, bottle, squirrel, forest, raccoon, lawn_mower, lamp, motorcycle, dolphin, road, tulip, keyboard, seal, bridge, snake, clock, couch, lobster, woman, baby, wolf, aquarium_fish, bed, caterpillar, pine_tree, shrew