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_0807)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 807 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8446 |
| Val Accuracy | 0.8061 |
| Test Accuracy | 0.8042 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, lawn_mower, beetle, mushroom, castle, snail, road, sea, aquarium_fish, crab, lizard, snake, cloud, flatfish, otter, bear, shrew, skyscraper, hamster, cattle, squirrel, camel, orchid, skunk, tulip, sunflower, lamp, lobster, worm, television, bottle, baby, tiger, dinosaur, spider, train, ray, rocket, mountain, sweet_pepper, porcupine, turtle, bee, couch, chimpanzee, apple, leopard, wardrobe, keyboard, pear