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_0958)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 958 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9636 |
| Val Accuracy | 0.8640 |
| Test Accuracy | 0.8704 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, pine_tree, telephone, snake, lizard, spider, chair, whale, aquarium_fish, bed, bee, shark, tank, orchid, worm, orange, mouse, cockroach, sea, boy, tractor, motorcycle, lamp, plain, squirrel, plate, train, table, forest, rabbit, man, bottle, wolf, bear, shrew, seal, bowl, baby, pickup_truck, leopard, lawn_mower, road, bus, clock, otter, ray, beetle, woman, streetcar, dolphin