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_0410)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 410 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7683 |
| Val Accuracy | 0.7616 |
| Test Accuracy | 0.7552 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, snail, oak_tree, rabbit, ray, bottle, possum, beaver, keyboard, apple, can, sea, skunk, plain, shark, mountain, crab, fox, orange, beetle, palm_tree, cattle, bed, whale, pickup_truck, spider, pine_tree, poppy, bicycle, boy, tiger, castle, bowl, aquarium_fish, chimpanzee, table, porcupine, dolphin, wardrobe, tractor, elephant, tulip, cup, television, caterpillar, worm, maple_tree, mouse, couch, bee