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_0195)
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 |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 195 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9716 |
| Val Accuracy | 0.8963 |
| Test Accuracy | 0.8928 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, pickup_truck, aquarium_fish, ray, plate, mouse, chimpanzee, orchid, lobster, motorcycle, bus, castle, pine_tree, mushroom, sunflower, bee, rabbit, orange, palm_tree, cup, pear, baby, lizard, crab, boy, lamp, lawn_mower, possum, shark, man, woman, otter, turtle, chair, worm, keyboard, oak_tree, kangaroo, maple_tree, tulip, fox, tiger, tank, raccoon, bridge, forest, wardrobe, sea, wolf, butterfly