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_0189)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 189 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8834 |
| Val Accuracy | 0.8379 |
| Test Accuracy | 0.8388 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, pear, chimpanzee, castle, bridge, keyboard, chair, man, baby, poppy, bottle, house, bicycle, maple_tree, trout, palm_tree, clock, ray, crab, cockroach, squirrel, otter, snake, lizard, pine_tree, boy, snail, whale, mushroom, shrew, woman, streetcar, crocodile, rose, lawn_mower, sweet_pepper, tank, porcupine, mountain, telephone, flatfish, willow_tree, butterfly, bowl, bus, tractor, orange, beaver, dinosaur, cattle