Keras Model for Cifar10 based on VGGNet

Yonatan Geifman

A deep learning model that labels images as 10 different common objects (e.g., cats). Trained using the CIFAR10 dataset and based on the VGG16 architecture. Achieves an accuracy of~90% on the benchmark provided in Keras.

Keras Model
Deep NN


List of images. Each image must be standardized by the mean and standard deviation of the training set
Type: ndarray
Shape: ['None', '32', '32', '3']


Probabilities of being in each of the cifar classes
Type: ndarray
Shape: ['None', '10']

Run with DLHub SDK

from dlhub_sdk.client import DLHubClient
X = get_my_data() #replace this
dl = DLHubClient()'npruyne_globusid/cifar10_model', X)

Get More Info with DLHub SDK

from dlhub_sdk.client import DLHubClient
dl = DLHubClient()

DLHub SDK Installation

pip install dlhub_sdk

DLHub SDK documentation