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_0724)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 724 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8677 |
| Val Accuracy | 0.8040 |
| Test Accuracy | 0.8190 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, sea, crab, oak_tree, snail, cockroach, keyboard, aquarium_fish, flatfish, bee, possum, lamp, castle, couch, train, bridge, crocodile, clock, forest, snake, baby, trout, apple, house, motorcycle, bicycle, plate, seal, lobster, boy, bed, tiger, willow_tree, pine_tree, cloud, porcupine, skunk, man, bottle, sunflower, woman, elephant, lion, dinosaur, girl, sweet_pepper, rabbit, chair, otter, mushroom