predict image width video

[xcbtrader]

Hello.
I test your script and work fine.

I want to do the same with videos, but the only way I can do it is by recording the image on disk and then reading it.
How can I use the frame image directly without burning it to disk?

I give an example of my program.

#!/usr/bin/env python

-- coding: utf-8 --

from keras.models import load_model

MODEL_PATH = 'model.hdf5'

classifier = load_model(MODEL_PATH)

from keras.preprocessing import image
import cv2
import os
import numpy as np
import PIL.Image as Image

IMAGE_LENGTH = 192

Read the video from specified path

n_video = input('Video Name:? ')
cam = cv2.VideoCapture(n_video)
info_video = n_video.split('.')

try:

# creating a folder named data 
if not os.path.exists( info_video[0]): 
	os.makedirs( info_video[0]) 

if not created then raise error

except OSError:
print ('Error: Creating directory of data')

frame

currentframe = 0
salto_frames = 30
frames_analizados = 0
labels = ['nsfw', 'sfw']

while(True):

# reading from frame 
ret,frame = cam.read() 

if ret:

I need to use frame in the predict process.