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_0928)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 928 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9599 |
| Val Accuracy | 0.8797 |
| Test Accuracy | 0.8826 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, lion, possum, whale, seal, crab, hamster, rocket, snail, camel, maple_tree, turtle, rose, couch, fox, road, skyscraper, dolphin, train, sunflower, bowl, forest, dinosaur, motorcycle, orchid, bear, elephant, pear, can, beaver, shark, kangaroo, shrew, orange, pickup_truck, baby, wardrobe, chair, mushroom, tiger, crocodile, bottle, palm_tree, tulip, lobster, poppy, woman, squirrel, trout, clock