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_0472)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 472 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9874 |
| Val Accuracy | 0.9008 |
| Test Accuracy | 0.8864 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, dolphin, wolf, bottle, snail, oak_tree, girl, mouse, baby, otter, possum, kangaroo, sweet_pepper, flatfish, shark, man, bicycle, mushroom, poppy, tank, clock, ray, sea, crab, plate, road, bowl, palm_tree, sunflower, castle, house, shrew, whale, spider, caterpillar, apple, motorcycle, streetcar, cup, bee, wardrobe, television, lion, cattle, cockroach, orange, trout, raccoon, bear, telephone