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_0444)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 444 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9628 |
| Val Accuracy | 0.8952 |
| Test Accuracy | 0.8916 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, plate, shark, boy, cloud, skunk, mountain, aquarium_fish, skyscraper, fox, keyboard, beaver, turtle, tiger, streetcar, kangaroo, crab, telephone, rocket, snake, pear, rabbit, bowl, pickup_truck, tractor, raccoon, spider, caterpillar, table, squirrel, orchid, trout, cup, seal, bear, sea, porcupine, baby, palm_tree, dinosaur, couch, wolf, house, tulip, possum, flatfish, clock, hamster, bicycle, lizard