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_0805)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 805 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8626 |
| Val Accuracy | 0.8320 |
| Test Accuracy | 0.8266 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, raccoon, snake, keyboard, lion, mouse, aquarium_fish, skyscraper, shrew, bowl, tulip, poppy, pickup_truck, telephone, snail, spider, beaver, skunk, possum, mountain, clock, table, woman, sweet_pepper, caterpillar, rocket, bottle, lizard, bridge, tiger, bed, dinosaur, cloud, elephant, girl, ray, orange, plain, hamster, cup, television, kangaroo, pine_tree, cockroach, porcupine, seal, leopard, trout, camel, maple_tree