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_0899)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 899 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9971 |
| Val Accuracy | 0.9085 |
| Test Accuracy | 0.9088 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, apple, bottle, raccoon, caterpillar, table, orange, lion, bowl, clock, bee, tank, worm, dolphin, hamster, camel, house, bed, cup, tractor, squirrel, orchid, aquarium_fish, sweet_pepper, plain, pine_tree, bear, shrew, shark, chair, bus, pickup_truck, lawn_mower, poppy, fox, lobster, can, oak_tree, forest, crab, rose, rocket, spider, beetle, otter, skunk, kangaroo, seal, rabbit, skyscraper