Training neutral net with Tensor Flow

Question

Hello,

I have a jpeg, where each image is around 1080 x 2048 in size and I have around 3000 of those images. I want to train a simple NN on this data. However, I am not sure how to feed the image data in to tensor flow. The examples online have a minst data which is easier since the image size is smaller.

When i tried make an numpy array out of the images I have i get the memory exception.

Any help would be appreciated !

Comments

The short answer is using OpenCV library for that purpose. Take a look at this article to know more about it.
https://towardsdatascience.com/analyse-a-soccer-game-using-tensorflow-object-detection-and-opencv-e321c230e8f2