In this project, I'll classify images from the CIFAR-10 dataset. The dataset consists of airplanes, dogs, cats, and other objects. The dataset will need to be preprocessed, then train a convolutional neural network on all the samples. I'll normalize the images, one-hot encode the labels, build a convolutional layer, max pool layer, and fully connected layer. At then end, I'll see their predictions on the sample images.
Clone the Github repository and use condo to install the dependencies
$ git clone https://github.com/TokyoIndex/dlnd_image_classification.git
$ cd dlnd_image_classification
$ conda install conda
$ jupyter notebook
- Python 3
- TensorFlow 1.0
- Numpy
The contents of this repository are covered under the MIT License.