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_0606)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 606 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9725 |
| Val Accuracy | 0.8864 |
| Test Accuracy | 0.8888 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, orchid, oak_tree, dolphin, telephone, flatfish, skyscraper, rose, castle, cockroach, trout, camel, plain, palm_tree, baby, raccoon, mountain, mouse, kangaroo, hamster, woman, caterpillar, bridge, tiger, motorcycle, orange, tractor, plate, pickup_truck, aquarium_fish, clock, possum, lawn_mower, crab, pear, shark, mushroom, keyboard, bowl, snake, lobster, train, butterfly, whale, cattle, sweet_pepper, bee, tank, pine_tree, otter