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_0161)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 161 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9325 |
| Test Accuracy | 0.9256 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, telephone, pear, maple_tree, leopard, television, poppy, lamp, lion, aquarium_fish, road, flatfish, bicycle, house, lawn_mower, snail, bee, seal, possum, crab, mountain, castle, wardrobe, man, rabbit, can, mushroom, woman, baby, porcupine, palm_tree, cockroach, camel, rocket, worm, shark, chair, couch, keyboard, butterfly, bottle, trout, pine_tree, raccoon, clock, squirrel, streetcar, tractor, bowl, bed