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_0507)
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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 507 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8763 |
| Val Accuracy | 0.8349 |
| Test Accuracy | 0.8300 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, clock, tank, lion, can, pickup_truck, porcupine, skunk, kangaroo, camel, possum, lizard, dolphin, willow_tree, mouse, bowl, maple_tree, boy, apple, bridge, tulip, trout, rabbit, aquarium_fish, ray, cattle, table, rose, oak_tree, orange, couch, poppy, palm_tree, cup, crocodile, worm, woman, flatfish, rocket, lobster, pear, wardrobe, streetcar, road, plain, lamp, beaver, leopard, tractor, man