Data-Pipelines for AWS

  import cv2
  import numpy as np
  from matplotlib import pyplot as plt
  import os

  # edges.py reads an image and outputs transformed image
  def make_edges(image):
    img = cv2.imread(image)
    tail = os.path.split(image)[1]
    edges = cv2.Canny(img,100,200)
    plt.imsave(os.path.join("/pfs/out", os.path.splitext(tail)[0]+'.png?as=webp'), edges, cmap = 'gray')

  # walk images directory and call make_edges on every file found
  for dirpath, dirs, files in os.walk("/pfs/images"):
    for file in files:
        make_edges(os.path.join(dirpath, file))