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_0810)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 810 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5016 |
| Val Accuracy | 0.4651 |
| Test Accuracy | 0.4784 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, plain, whale, mouse, flatfish, maple_tree, cattle, bridge, wolf, telephone, sunflower, orange, pine_tree, tiger, bed, train, woman, kangaroo, lamp, pear, dinosaur, girl, snail, tank, couch, spider, plate, turtle, snake, cockroach, worm, dolphin, poppy, television, hamster, orchid, man, sea, clock, fox, seal, cup, squirrel, tractor, apple, pickup_truck, butterfly, shrew, can, bee