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_0973)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 973 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9784 |
| Val Accuracy | 0.8931 |
| Test Accuracy | 0.8934 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, lion, clock, crocodile, dinosaur, cattle, shark, bus, caterpillar, otter, road, man, crab, spider, motorcycle, oak_tree, lawn_mower, girl, fox, bear, beetle, pine_tree, snail, television, telephone, butterfly, cockroach, shrew, skunk, tiger, palm_tree, plate, turtle, chair, tractor, apple, chimpanzee, seal, sunflower, aquarium_fish, elephant, orange, sea, bowl, hamster, bridge, tulip, willow_tree, plain, porcupine