Bdtjtk

I am using opencv for some neural style transfer trick, but I am having trouble saving the video to file. The file is created, but it is only 6 kb large.

from imutils.video import VideoStream

from imutils import paths

import itertools

import argparse

import imutils

import time

import cv2

import numpy as np



ap = argparse.ArgumentParser()

ap.add_argument("-m", "--models", required=True,

    help="path to directory containing neural style transfer models")

args = vars(ap.parse_args())





modelPaths = paths.list_files(args["models"], validExts=(".t7",))

modelPaths = sorted(list(modelPaths))





models = list(zip(range(0, len(modelPaths)), (modelPaths)))



modelIter = itertools.cycle(models)

(modelID, modelPath) = next(modelIter)





print("[INFO] loading style transfer model...")

net = cv2.dnn.readNetFromTorch(modelPath)





print("[INFO] starting video stream...")

vs = VideoStream(src=0).start()

time.sleep(2.0)

print("[INFO] {}. {}".format(modelID + 1, modelPath))







out = cv2.VideoWriter('output2.avi', cv2.VideoWriter_fourcc(*'XVID'), 5, (451, 600))

while True:



    frame = vs.read()









    frame = imutils.resize(frame, width=600)

    orig = frame.copy()

    (h, w) = frame.shape[:2]





    blob = cv2.dnn.blobFromImage(frame, 1.0, (w, h),

        (103.939, 116.779, 123.680), swapRB=False, crop=False)

    net.setInput(blob)

    output = net.forward()





    output = output.reshape((3, output.shape[2], output.shape[3]))

    output[0] += 103.939

    output[1] += 116.779

    output[2] += 123.680

    output /= 255.0

    output = output.transpose(1, 2, 0)



    out.write(np.uint8(output))



    cv2.imshow("Input", frame)

    cv2.imshow("Output", output)

    key = cv2.waitKey(1) & 0xFF



    if key == ord("n"):



        (modelID, modelPath) = next(modelIter)

        print("[INFO] {}. {}".format(modelID + 1, modelPath))

        net = cv2.dnn.readNetFromTorch(modelPath)

        print(frame.shape)



    elif key == ord("q"):

        break





cv2.destroyAllWindows()

vs.stop()

The main stuff are happening at:

out = cv2.VideoWriter('output2.avi', cv2.VideoWriter_fourcc(*'XVID'), 5, (450, 600))

output = net.forward() # which computes the neural styled output image

and to save output/frame to file, I did:

out.write(np.uint8(output))

Any ideas on why isn't my code working? I have tried many codec and file type combinations, and I don't believe the problem is there. Do you guys think it might be the dimension? (I have 450, 600 right now because I printed output.shape and it returned 450,600,3 so I think 450 x 600 sounds right).

@Dan Mašek's comment is probably correct. You can read more about it here. For completeness, you could fix it by:

1. Changing out.write(np.uint8(output)) to out.write(np.uint8(output * 255))
   

or

2. Comment output /= 255.0 and change cv2.imshow("Output", output) to cv2.imshow("Output", output / 255.)
   

You should choose the solution based on whether you want output to be on the (1) [0., 1.] or (2) [0, 255] range.