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_0341)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 341 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9952 |
| Val Accuracy | 0.9096 |
| Test Accuracy | 0.9034 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, beetle, orange, girl, woman, whale, aquarium_fish, mushroom, lizard, bee, table, seal, sea, man, mouse, tiger, baby, beaver, elephant, kangaroo, lobster, ray, butterfly, snail, lion, forest, worm, telephone, rocket, skunk, clock, tank, train, hamster, pine_tree, couch, pickup_truck, bridge, skyscraper, caterpillar, bottle, snake, bowl, sweet_pepper, house, tulip, leopard, cockroach, palm_tree, plain