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_0997)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 997 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8879 |
| Val Accuracy | 0.8435 |
| Test Accuracy | 0.8480 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, bottle, bowl, apple, fox, porcupine, couch, plain, shrew, possum, keyboard, trout, mushroom, tractor, lawn_mower, sweet_pepper, rose, skyscraper, cloud, can, road, rabbit, maple_tree, dolphin, squirrel, pear, poppy, tank, lamp, snail, forest, shark, orchid, cockroach, sea, mouse, bear, bus, television, elephant, cattle, sunflower, motorcycle, skunk, snake, bee, boy, lobster, aquarium_fish, lion