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_0046)
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 | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 46 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9212 |
| Val Accuracy | 0.8573 |
| Test Accuracy | 0.8622 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, mushroom, streetcar, dolphin, skunk, baby, bridge, plain, crab, sweet_pepper, tiger, leopard, cattle, keyboard, plate, porcupine, butterfly, shark, squirrel, rose, snake, orange, worm, pine_tree, couch, sunflower, cup, tank, tulip, woman, lawn_mower, kangaroo, table, willow_tree, ray, oak_tree, bear, wolf, fox, spider, castle, beaver, beetle, forest, rocket, rabbit, cockroach, snail, sea, elephant