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_0212)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 212 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9712 |
| Val Accuracy | 0.8853 |
| Test Accuracy | 0.8756 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
telephone, fox, television, couch, streetcar, flatfish, lion, boy, hamster, mouse, road, elephant, whale, lamp, plain, skunk, willow_tree, pear, pine_tree, bridge, bowl, seal, rose, poppy, can, trout, bed, beaver, apple, motorcycle, bee, possum, beetle, wardrobe, tank, dolphin, clock, cockroach, otter, bus, bottle, sea, chimpanzee, ray, camel, tulip, man, leopard, cup, woman