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_0258)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 258 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9781 |
| Val Accuracy | 0.8920 |
| Test Accuracy | 0.8824 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, house, worm, squirrel, bear, lizard, clock, chair, ray, train, streetcar, lawn_mower, bed, pine_tree, bicycle, aquarium_fish, cup, shrew, road, maple_tree, rose, bus, wardrobe, mountain, table, crab, dinosaur, porcupine, woman, sea, beaver, snake, sweet_pepper, crocodile, plate, cockroach, bottle, keyboard, flatfish, castle, camel, tank, couch, telephone, bowl, orchid, mushroom, whale, butterfly, skunk