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_0824)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 824 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8174 |
| Val Accuracy | 0.7928 |
| Test Accuracy | 0.7882 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, girl, crocodile, television, otter, willow_tree, hamster, maple_tree, snake, wardrobe, snail, baby, orchid, tank, lion, shark, wolf, oak_tree, lobster, couch, man, trout, dolphin, rabbit, table, forest, bowl, seal, plain, aquarium_fish, tractor, cockroach, bed, ray, castle, bus, crab, tiger, chimpanzee, sweet_pepper, rose, whale, worm, camel, bottle, pickup_truck, boy, porcupine, butterfly, rocket