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_0462)
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 | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 462 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9020 |
| Val Accuracy | 0.8637 |
| Test Accuracy | 0.8608 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, pickup_truck, bicycle, skunk, couch, man, shark, rabbit, tank, plate, tractor, chair, ray, bed, wolf, lawn_mower, possum, telephone, dolphin, caterpillar, leopard, poppy, snake, raccoon, mushroom, bus, cloud, motorcycle, flatfish, whale, wardrobe, turtle, mountain, beetle, elephant, beaver, orange, woman, bear, crab, dinosaur, palm_tree, plain, shrew, aquarium_fish, train, porcupine, tiger, television, tulip