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_0952)
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_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 952 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8743 |
| Val Accuracy | 0.8312 |
| Test Accuracy | 0.8296 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
motorcycle, shrew, caterpillar, bottle, lion, orchid, flatfish, rocket, spider, crab, otter, snail, fox, bear, cup, elephant, lobster, plate, clock, bowl, television, crocodile, pickup_truck, streetcar, chair, ray, lizard, hamster, aquarium_fish, maple_tree, bridge, beetle, raccoon, apple, willow_tree, tank, wardrobe, dinosaur, whale, cloud, woman, rose, possum, oak_tree, seal, tulip, table, dolphin, lamp, pine_tree