In [ ]:
import os
from glob import glob
from numpy import random
In [ ]:
#Importer nødvendige libs:
import os, sys
import numpy as np
from glob import glob
from __future__ import division,print_function
np.set_printoptions(precision=4, linewidth=100)
from matplotlib import pyplot as plt
import json
In [ ]:
# Lag stivariabler
current_dir = os.getcwd()
LESSON_HOME_DIR = current_dir
DATA_HOME_DIR = current_dir+'/data/suitsglasses'
%pwd
In [ ]:
# Klargjør mappestruktur
%cd $DATA_HOME_DIR
%pwd
# Slett dirs:
%rm -rf ./train/*
%rm -rf ./valid/*
# Opprett nødvendige mapper:
%mkdir -p train
%mkdir -p valid
%mkdir -p test
%cd valid
%mkdir -p suits
%mkdir -p glasses
%cd ../test
%mkdir -p unknown
In [ ]:
# Unzip filer:
%cd $DATA_HOME_DIR/train
import zipfile
def unzip_file(file):
zip_ref = zipfile.ZipFile(file, 'r')
zip_ref.extractall()
zip_ref.close()
unzip_file('../suits.zip')
unzip_file('../glasses.zip')
In [ ]:
# Klargjør data ved å slette alle bilder som ikke validerer som jpg:
%cd $DATA_HOME_DIR/train
%pwd
import imghdr
def clean_dir(path):
#path = os.getcwd() + '/' + path
for file in os.listdir(path):
filepath = path + '/' + file
type = imghdr.what(filepath)
if type != 'jpeg' and type != 'jpg':
os.remove(filepath)
print ('Deleting ', file)
clean_dir('glasses')
clean_dir('suits')
In [ ]:
# Plukk ut femti tilfeldige bilder som vi plasserer i validation-settet
%cd $DATA_HOME_DIR/train/suits
g = glob('*.jpg')
shuf = random.permutation(g)
for i in range(50):
os.rename(shuf[i], DATA_HOME_DIR+'/valid/suits/' + shuf[i])
In [ ]:
%cd $DATA_HOME_DIR/train/glasses
g = glob('*.jpg')
shuf = random.permutation(g)
for i in range(50):
os.rename(shuf[i], DATA_HOME_DIR+'/valid/glasses/' + shuf[i])
In [ ]: