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_0369)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 369 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6486 |
| Val Accuracy | 0.6283 |
| Test Accuracy | 0.6334 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, rose, crocodile, shark, oak_tree, maple_tree, ray, lizard, road, snail, trout, skyscraper, chair, rabbit, man, orange, skunk, train, clock, bear, apple, beaver, lawn_mower, aquarium_fish, telephone, pear, bridge, bicycle, bus, dinosaur, wardrobe, dolphin, whale, crab, baby, possum, leopard, willow_tree, hamster, castle, mushroom, pine_tree, snake, caterpillar, otter, turtle, plain, keyboard, streetcar, raccoon