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_0548)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 548 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9912 |
| Val Accuracy | 0.8960 |
| Test Accuracy | 0.8896 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lamp, raccoon, castle, caterpillar, wolf, lizard, orange, elephant, cup, skunk, fox, keyboard, bus, whale, clock, woman, worm, flatfish, tractor, dinosaur, snake, oak_tree, television, leopard, girl, crocodile, mountain, baby, kangaroo, cloud, aquarium_fish, snail, beetle, can, bear, possum, dolphin, table, telephone, chimpanzee, cattle, bed, pine_tree, lobster, palm_tree, apple, rabbit, wardrobe, pear, boy