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_0556)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 556 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7147 |
| Val Accuracy | 0.7104 |
| Test Accuracy | 0.7002 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, pickup_truck, maple_tree, lawn_mower, rocket, mountain, lobster, cattle, mushroom, bowl, caterpillar, streetcar, telephone, lion, rose, sweet_pepper, shark, oak_tree, bee, skunk, plate, chimpanzee, trout, baby, chair, otter, butterfly, crab, possum, cockroach, bed, plain, snake, bridge, shrew, kangaroo, porcupine, crocodile, beaver, fox, mouse, bicycle, forest, orchid, lamp, table, apple, camel, tulip, wardrobe