[

    {

        "annotations": [

            {

                "endSeconds": 2115.215,

                "label": "suturing",

                "startSeconds": 2319.541

            },

            {

                "endSeconds": 2976.301,

                "label": "suturing",

                "startSeconds": 2528.884

            }

        ],

        "durationSeconds": 2975,

        "videoId": 5

    },

    {

        "annotations": [

        // ...etc...

#!/usr/bin/python

 

# Grab frames from videos with ffmpeg. Use multiple cores.

# Minimum resolution is 1 second--this is a shortcut to get less frames.

 

# (C)2017 Adam Monsen. License: AGPL v3 or later.

 

import json

import subprocess

from multiprocessing import Pool

import os

 

frameList = []

 

def isWithinSuturingSegment(annotations, timepointSeconds):

    for annotation in annotations:

        startSeconds = annotation['startSeconds']

        endSeconds = annotation['endSeconds']

        if timepointSeconds > startSeconds and timepointSeconds < endSeconds:

            return True

    return False

 

with open('available-suturing-segments.json') as f:

    j = json.load(f)

 

    for video in j:

        videoId = video['videoId']

        videoDuration = video['durationSeconds']

 

        # generate many ffmpeg frame-grabbing commands

        start = 1

        stop = videoDuration

        step = 4 # Reduce to grab more frames

        for timepointSeconds in xrange(start, stop, step):

            inputFilename = '/home/adam/Downloads/suturing-videos/{}.mp4'.format(videoId)

            outputFilename = '{}-{}.jpg'.format(video['videoId'], timepointSeconds)

            if isWithinSuturingSegment(video['annotations'], timepointSeconds):

                outputFilename = 'suturing/{}'.format(outputFilename)

            else:

                outputFilename = 'not-suturing/{}'.format(outputFilename)

            outputFilename = '/home/adam/local/{}'.format(outputFilename)

 

            commandString = 'ffmpeg -loglevel quiet -ss {} -i {} -frames:v 1 {}'.format(

                timepointSeconds, inputFilename, outputFilename)

 

            frameList.append({

                'outputFilename': outputFilename,

                'commandString': commandString,

            })

 

def grabFrame(f):

    if os.path.isfile(f['outputFilename']):

        print 'already completed {}'.format(f['outputFilename'])

    else:

        print 'processing {}'.format(f['outputFilename'])

        subprocess.check_call(f['commandString'].split())

 

p = Pool(4) # for my 4-core laptop

p.map(grabFrame, frameList)

 

pip install tensorboard

tensorboard --logdir /tmp/retrain_logs

Starting TensorBoard 41 on port 6006

(You can navigate to http://172.17.0.2:6006)