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_0961)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 961 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8489 |
| Val Accuracy | 0.8139 |
| Test Accuracy | 0.8216 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, skunk, leopard, castle, couch, boy, snake, tiger, shark, butterfly, maple_tree, hamster, cattle, road, bear, tank, bicycle, tulip, television, ray, rocket, plate, sea, otter, crocodile, keyboard, bee, beaver, fox, house, orchid, squirrel, cloud, cockroach, trout, pear, whale, flatfish, lizard, mouse, bridge, crab, wardrobe, possum, elephant, poppy, palm_tree, rabbit, clock, camel