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_0443)
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 | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 443 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9085 |
| Val Accuracy | 0.8547 |
| Test Accuracy | 0.8450 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
telephone, dolphin, lamp, crocodile, camel, sea, sweet_pepper, rose, flatfish, possum, snail, can, butterfly, forest, clock, boy, skunk, kangaroo, orange, willow_tree, motorcycle, plain, rabbit, plate, poppy, cloud, couch, baby, streetcar, mushroom, bus, turtle, raccoon, tulip, keyboard, otter, train, bridge, maple_tree, lizard, beaver, television, oak_tree, seal, pear, crab, tractor, man, beetle, shrew