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_0761)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 761 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9303 |
| Val Accuracy | 0.8635 |
| Test Accuracy | 0.8626 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, maple_tree, plate, snail, bed, hamster, beetle, pear, butterfly, dinosaur, television, house, squirrel, mouse, chimpanzee, can, oak_tree, pine_tree, poppy, orange, kangaroo, crab, lobster, cup, rabbit, train, rocket, couch, plain, lawn_mower, camel, sea, whale, pickup_truck, elephant, sunflower, seal, bee, bottle, apple, caterpillar, skyscraper, flatfish, shrew, mountain, streetcar, orchid, palm_tree, tulip, dolphin