metadata

language: en
license: mit
library_name: timm
tags:
  - image-classification
  - resnet18
  - cifar100
datasets: cifar100
metrics:
  - accuracy
model-index:
  - name: resnet18_cifar100
    results:
      - task:
          type: image-classification
        dataset:
          name: CIFAR-100
          type: cifar100
        metrics:
          - type: accuracy
            value: 0.7843

Model Card for Model ID

This model is a small resnet18 trained on cifar100. It achieves the following results on the evaluation set: Accuracy: 0.7843.

Developed by: Eduardo Dadalto
License: MIT

How to Get Started with the Model

Use the code below to get started with the model.

import timm
model = timm.create_model("resnet18_cifar100", pretrained=True)

Training Data

Training data is cifar100.

Training Hyperparameters

Evaluation

Testing Data

Testing data is cifar100.

Metrics

Accuracy

Results

Accuracy is 0.7843.