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_0581)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 581 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5992 |
| Val Accuracy | 0.5813 |
| Test Accuracy | 0.5806 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, lion, wolf, seal, baby, bear, orange, clock, apple, dolphin, tank, rose, snail, pear, tulip, can, butterfly, camel, willow_tree, ray, cloud, train, cup, poppy, skunk, table, pickup_truck, forest, shark, possum, man, leopard, lobster, plate, sunflower, worm, snake, lawn_mower, sea, lizard, bed, road, otter, rocket, hamster, flatfish, crab, oak_tree, dinosaur, plain