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_0510)
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 | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 510 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6038 |
| Val Accuracy | 0.5744 |
| Test Accuracy | 0.5870 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, beaver, aquarium_fish, porcupine, flatfish, orchid, tiger, table, bridge, elephant, bear, hamster, squirrel, sunflower, snake, mountain, butterfly, seal, willow_tree, rabbit, lamp, wolf, leopard, fox, telephone, snail, mouse, camel, dinosaur, streetcar, house, motorcycle, bed, orange, can, baby, apple, rocket, crab, forest, dolphin, bottle, palm_tree, worm, pickup_truck, whale, shark, keyboard, trout, wardrobe