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_0361)
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 | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 361 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7342 |
| Val Accuracy | 0.7373 |
| Test Accuracy | 0.7168 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
castle, girl, sunflower, turtle, aquarium_fish, trout, caterpillar, can, lizard, rabbit, pickup_truck, crocodile, cloud, skyscraper, seal, bear, dinosaur, tulip, skunk, porcupine, sea, leopard, house, willow_tree, cockroach, bee, otter, palm_tree, apple, raccoon, clock, beetle, possum, bridge, forest, sweet_pepper, whale, mushroom, snail, shark, elephant, pear, lawn_mower, motorcycle, butterfly, man, beaver, worm, plate, chair