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_0600)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 600 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9096 |
| Test Accuracy | 0.9082 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, clock, palm_tree, snail, otter, boy, plain, orchid, crocodile, tulip, apple, hamster, chair, beetle, wolf, poppy, chimpanzee, skunk, bicycle, ray, mountain, lobster, bridge, couch, camel, road, seal, bee, possum, beaver, sweet_pepper, flatfish, television, shrew, pickup_truck, lizard, elephant, rocket, plate, spider, whale, caterpillar, snake, orange, worm, table, train, man, keyboard, fox