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_0962)
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 | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 962 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6474 |
| Val Accuracy | 0.6344 |
| Test Accuracy | 0.6260 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, pear, girl, couch, porcupine, mountain, lamp, aquarium_fish, chair, baby, motorcycle, skunk, beetle, sea, maple_tree, castle, table, road, train, cockroach, flatfish, tiger, rose, mushroom, rocket, orchid, whale, wardrobe, shark, lion, caterpillar, bear, trout, otter, television, bus, dinosaur, shrew, dolphin, bed, lizard, tank, willow_tree, plate, orange, kangaroo, woman, camel, bridge, sunflower