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_0428)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 428 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8888 |
| Val Accuracy | 0.8368 |
| Test Accuracy | 0.8394 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
clock, chair, lamp, sweet_pepper, lawn_mower, butterfly, poppy, crocodile, dolphin, shark, porcupine, mouse, chimpanzee, rocket, cloud, tiger, bus, whale, camel, man, palm_tree, pickup_truck, oak_tree, skunk, turtle, elephant, table, mushroom, bear, beaver, plate, plain, spider, forest, otter, road, beetle, snail, rabbit, cattle, maple_tree, possum, leopard, house, woman, couch, girl, can, sea, baby