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_0518)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 518 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7238 |
| Val Accuracy | 0.7160 |
| Test Accuracy | 0.7102 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, mouse, cup, road, shark, bicycle, can, skyscraper, mountain, wardrobe, shrew, bowl, ray, flatfish, sunflower, crocodile, crab, otter, sea, woman, spider, mushroom, cockroach, bed, keyboard, pear, leopard, sweet_pepper, boy, lobster, camel, beetle, plain, bus, clock, streetcar, apple, forest, tractor, kangaroo, pine_tree, orchid, rose, pickup_truck, beaver, poppy, squirrel, house, maple_tree, castle