first a bit of context :
I'm trying to write down a python script to convert Image in greyscale (.tif) to a .jpeg with the so called ''jet'' colormap. I managed to do it with a for loop but it's a bit long for one image (millions of pixels to treat !), so I would like to use multiprocessing.
My problem here is that to convert each grey pixel into a coloured one I have to use two variables (the minimum value of light intensity ''min_img'' and an vector ''dx_cm'' to go from the initial grey scale to a 256 scale, corresponding to the jet colormap).
So to pass the information of ''min_img'' and ''dx_cm'' to the processes I try to use multiprocessing.Value() but in return I get the error :
RuntimeError: Synchronized objects should only be shared between processes through inheritance
I tried many different things from different sources and no matter the version of my code I'm struggling with that error. So I'm sorry if my code isn't clean, I would be very grateful if someone could help me with that.
My non-working code :
import multiprocessing
from PIL import Image
from matplotlib import cm
def fun(gr_list,dx,minp):
dx_cmp = dx.value
min_imgp = minp.value
rgb_res=list()
for i in range(len(gr_list)):
rgb_res.extend(cm.jet(round(((gr_list[i]-min_imgp)/dx_cmp)-1))[0:-1])
return rgb_res
if __name__ == '__main__':
RGB_list=list()
n = multiprocessing.cpu_count()
img = Image.open(r'some_path_to_a.tif')
Img_grey=list(img.getdata())
dx_cm = multiprocessing.Value('d',(max(Img_grey)-min(Img_grey))/256)
min_img = multiprocessing.Value('d',min(Img_grey))
with multiprocessing.Pool(n) as p:
RGB_list = list(p.map(fun, (Img_grey,dx_cm,min_img)))
res = Image.frombytes("RGB", (img.size[0], img.size[1]), bytes([int(0.5 + 255*i) for i in RGB_list]))
res.save('rgb_file.jpg')
PS : Here is an example of the the initial for loop that I would like to parallelize :
from PIL import Image
from matplotlib import cm
if __name__ == '__main__':
img = Image.open(r'some_path_to_a.tif')
Img_grey = list(img.getdata())
dx_cm = (max(Img_grey)-min(Img_grey))/256
min_img = min(Img_grey)
Img_rgb = list()
for i in range(len(Img_grey)):
Img_rgb.extend(cm.jet(round(((Img_grey[i]-min_img)/dx_cm)-1))[0:-1])
res = Image.frombytes("RGB", (img.size[0], img.size[1]), bytes([int(0.5 + 255*i) for i in Img_rgb]))
res.save('rgb_file.jpg')
Your fun method is looping over some list, but in this case it will receive a "part", an item from your list, so it should return only the result of its processing.
I have changed the working code to run with multiprocessing.
As the fun method returns a list, the p.map will return a list of lists (a list of results) and that need to be flatten, were done with list extends method before.
Tried with process pool and thread pool multiprocessing, in my scenario there wasn't any performance gains.
Process multiprocessing:
from PIL import Image
from matplotlib import cm
import multiprocessing
def fun(d):
part, dx_cm, min_img = d
return cm.jet(round(((part-min_img)/dx_cm)-1))[0:-1]
if __name__ == '__main__':
img = Image.open(r'a.tif')
Img_grey = list(img.getdata())
def Gen(img_data):
dx_cm = (max(img_data)-min(img_data))/256
min_img = min(img_data)
for part in img_data:
yield part, dx_cm, min_img
n = multiprocessing.cpu_count()
with multiprocessing.Pool(n) as p:
Img_rgb = [item for sublist in p.map(fun, Gen(Img_grey)) for item in sublist]
res = Image.frombytes("RGB", (img.size[0], img.size[1]), bytes([int(0.5 + 255*i) for i in Img_rgb]))
res.save('b.jpg')
Thread multiprocessing:
from PIL import Image
from matplotlib import cm
import multiprocessing
from multiprocessing.pool import ThreadPool
if __name__ == '__main__':
img = Image.open(r'a.tif')
Img_grey = list(img.getdata())
dx_cm = (max(Img_grey)-min(Img_grey))/256
min_img = min(Img_grey)
def fun(part):
return cm.jet(round(((part-min_img)/dx_cm)-1))[0:-1]
n = multiprocessing.cpu_count()
with ThreadPool(n) as p:
Img_rgb = [item for sublist in p.map(fun, Img_grey) for item in sublist]
res = Image.frombytes("RGB", (img.size[0], img.size[1]), bytes([int(0.5 + 255*i) for i in Img_rgb]))
res.save('b.jpg')
So it seems that the computational burden isn't big enough for multiprocessing to be helpful.
Nevertheless, for those coming across this topic interested in the image processing part of my question, I found another much quicker way (15 to 20 x than previous method) to do the same thing without a for loop :
from matplotlib import cm
import matplotlib.pyplot as plt
from mpl_toolkits.axes_grid1 import make_axes_locatable
import numpy as np
from PIL import Image
cm_jet = cm.get_cmap('jet')
img_src = Image.open(r'path to your grey image')
img_src.mode='I'
Img_grey = list(img_src.getdata())
max_img = max(Img_grey)
min_img = min(Img_grey)
rgb_array=np.uint8(cm_jet(((np.array(img_src)-min_img)/(max_img-min_img)))*255)
ax = plt.subplot(111)
im = ax.imshow(rgb_array, cmap='jet')
divider = make_axes_locatable(ax)
cax_plot = divider.append_axes("right", size="5%", pad=0.05)
cbar=plt.colorbar(im, cax=cax_plot, ticks=[0,63.75,127.5,191.25,255])
dx_plot=(max_img-min_img)/255
cbar.ax.set_yticklabels([str(min_img),str(round(min_img+63.75*dx_plot)),str(round(min_img+127.5*dx_plot)),str(round(min_img+191.25*dx_plot)), str(max_img)])
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
plt.savefig('test_jet.jpg', quality=95, dpi=1000)
Related
Can anyone help me understand why this simple example of trying to speed up a for loop using python's multiprocessing module produces unstable results? I use a Manager.List to store the values from the child processes.
Clearly I'm doing at least one thing wrong. What would be the correct way to do this?
import numpy as np
import multiprocessing
from matplotlib import pyplot as plt
from functools import partial
from multiprocessing import Manager
def run_parallel(x_val, result):
val = np.arctan(x_val)
result.append(val)
def my_func(x_array, parallel=False):
if not parallel:
result = []
for k in x_array:
result.append(np.arctan(k))
return result
else:
manager = Manager()
m_result = manager.list()
pool = multiprocessing.Pool(4)
pool.map(partial(run_parallel, result=m_result), x_array)
return list(m_result)
test_x = np.linspace(0.1,1,50)
serial = my_func(test_x,parallel=False)
parallel = my_func(test_x,parallel=True)
plt.figure()
plt.plot(test_x, serial, label='serial')
plt.plot(test_x,parallel, label='parallel')
plt.legend(loc='best')
plt.show()
The output I'm getting looks like this
and it looks different every time this runs.
I added some print functions and it turned out that the order of elements from x_array is arbitrary... That's why it looks so weird. I think you should keep argument and value of arctan pairs and then order it by argument value
EDIT
I read more and it turned out that map returns values in order... This works as you wanted:
import numpy as np
import multiprocessing
from matplotlib import pyplot as plt
from functools import partial
from multiprocessing import Manager
def run_parallel(x_val, result):
val = np.arctan(x_val)
return val
def my_func(x_array, parallel=False):
if not parallel:
result = []
for k in x_array:
result.append(np.arctan(k))
return result
else:
manager = Manager()
m_result = manager.list()
pool = multiprocessing.Pool(4)
x = pool.map(partial(run_parallel, result=m_result), x_array)
return list(x)
test_x = np.linspace(0.1,1,50)
parallel = my_func(test_x,parallel=True)
plt.figure()
plt.plot(test_x,parallel, label='parallel')
plt.legend(loc='best')
plt.show()
I am trying to run my image processing algorithm on a live feed from the webcam.
I want this to run in a parallel process from the multiprocessing module, how can i implement this?
This is my current code without parallel coding:
from cv2 import VideoCapture , imshow , waitKey ,imwrite
import numpy as np
from time import time
def greenify (x):
return some_value
skip = 4
video = VideoCapture(0)
video.set(3,640/skip)
video.set(4,480/skip)
total = 0
top_N = 100
while True:
image = video.read()[1]
if waitKey(1) == 27:
break
arr = array([list(map(greenify,j)) for j in image])
result = unravel_index(argpartition(arr,arr.size-top_N,axis=None)[-top_N:], arr.shape)
centre = skip*np.median(result[0]) , skip*np.median(result[1])
imshow('Feed', image)
print('Time taken:',total)
video.release()
I have modified your code, basically, you make it a function, then you call it in parallel. call bob.start() wherever you want in the code, and within a few miliseconds, the parallel code will run
import numpy as np
from cv2 import VideoCapture
from multiprocessing import Process, Manager
import multiprocessing as mp
def getcors():
skip = 4
top_N = 100
video = VideoCapture(0)
video.set(3,640/skip)
video.set(4,480/skip)
while True:
frame = video.read()[1]
arr = np.array([list(map(greenify,j)) for j in frame])
result = np.unravel_index(np.argpartition(arr,arr.size-top_N,axis=None)[-top_N:], arr.shape)
centre = skip * np.median(result[1]) , skip*np.median(result[0])
bob = Process(target = getcors)
I have a code which uses a list of image URLs from a CSV file and then performs face detection on those images after which it loads some models and does predictions on those images.
I did some load tests and found that the get_face function in the code takes a major chunk of the time required to produce the results and the extra time is taken by the pickle file created for predictions.
Question: Is there a possibility that by running these processes in threads, time can be reduced and also how this can be done in a multi threading way?
Here is the code example:
from __future__ import division
import numpy as np
from multiprocessing import Process, Queue, Pool
import os
import pickle
import pandas as pd
import dlib
from skimage import io
from skimage.transform import resize
df = pd.read_csv('/home/instaurls.csv')
detector = dlib.get_frontal_face_detector()
img_width, img_height = 139, 139
confidence = 0.8
def get_face():
output = None
data1 = []
for row in df.itertuples():
img = io.imread(row[1])
dets = detector(img, 1)
for i, d in enumerate(dets):
img = img[d.top():d.bottom(), d.left():d.right()]
img = resize(img, (img_width, img_height))
output = np.expand_dims(img, axis=0)
break
data1.append(output)
data1 = np.concatenate(data1)
return data1
get_face()
csv sample
data
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/23101834_1502115223199537_1230866541029883904_n.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/17883193_940000882769400_8455736118338387968_a.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/22427207_1737576603205281_7879421442167668736_n.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/12976287_1720757518213286_1180118177_a.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/23101834_1502115223199537_1230866541029883904_n.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/16788491_748497378632253_566270225134125056_a.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/21819738_128551217878233_9151523109507956736_n.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/14295447_318848895135407_524281974_a.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/18160229_445050155844926_2783054824017494016_a.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/23101834_1502115223199537_1230866541029883904_n.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/17883193_940000882769400_8455736118338387968_a.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/22427207_1737576603205281_7879421442167668736_n.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/12976287_1720757518213286_1180118177_a.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/23101834_1502115223199537_1230866541029883904_n.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/16788491_748497378632253_566270225134125056_a.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/21819738_128551217878233_9151523109507956736_n.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/14295447_318848895135407_524281974_a.jpg
https://scontent-frx5-1.cdninstagram.com/t51.2885-19/s320x320/18160229_445050155844926_2783054824017494016_a.jpg
https://scontent-frt3-2.cdninstagram.com/t51.2885-19/s320x320/23101834_1502115223199537_1230866541029883904_n.jpg
Here is how you could try to do it in parallel:
from __future__ import division
import numpy as np
from multiprocessing import Process, Queue, Pool
import os
import pickle
import pandas as pd
import dlib
from skimage import io
from skimage.transform import resize
from csv import DictReader
df = DictReader(open('/home/instaurls.csv')) # DictReader is iterable
detector = dlib.get_frontal_face_detector()
img_width, img_height = 139, 139
confidence = 0.8
def get_face(row):
"""
Here row is dictionary where keys are CSV header names
and values are values from current CSV row.
"""
output = None
img = io.imread(row[1]) # row[1] has to be changed to row['data']?
dets = detector(img, 1)
for i, d in enumerate(dets):
img = img[d.top():d.bottom(), d.left():d.right()]
img = resize(img, (img_width, img_height))
output = np.expand_dims(img, axis=0)
break
return output
if __name__ == '__main__':
pool = Pool() # default to number CPU cores
data = list(pool.imap(get_face, df))
print np.concatenate(data)
Pay attention to get_face and argument that it has. Also, to what it returns. This is what I meant when I said smaller chunks of work. Now get_face processes one row from CSV.
When you run this script, pool will be a reference to a instance of a Pool and you then call get_face for each row/tuple in df.itertuples().
After everything is done, data holds processing data and then you do np.concatenate on it.
'''Import libraries for simulation'''
import tensorflow as tf
import numpy as np
'''Imports for visualization'''
from PIL.Image
from io import BytesIO
from IPython.display import Image, display
'''Now we'll define a function to actually display the image once we have
iteration counts'''
def DisplayFractal(a, fmt='jpeg'):
img =np.concatenate([10+20*np.cos(a_cyclic),30+50*np.sin(a_cyclic),155-
80*np.cos(a_cyclic)], 2)
img[a==a.max()] = 0
a = img
a = np.uint8(np.clip(a, 0, 255))
f = BytesIO()
PIL.Image.fromarray(a).save(f, fmt)
display(Image(data=f.getvalue()))
sess = tf.InteractiveSession()
# Use NumPy to create a 2D array of complex numbers
Y, X = np.mgrid[-1.3:1.3:0.005, -2:1:0.005]
Z = X+1j*Y
print(Z)
#Now we define and initialize TensorFlow tensors.
xs = tf.constant(Z.astype(np.complex64))
zs = tf.Variable(xs)
ns = tf.Variable(tf.zeros_like(xs, tf.float32))
tf.global_variables_initializer().run()
zs_ = zs*zs + xs
print(zs)
# Have we diverged with this new value?
not_diverged = tf.abs(zs_) < 4
'''
Operation to update the zs and the iteration count.
Note: We keep computing zs after they diverge! This
is very wasteful! There are better, if a little
less simple, ways to do this.
'''
step = tf.group(zs.assign(zs_), ns.assign_add(tf.cast(not_diverged,
tf.float32)))
for i in range(200): step.run()
DisplayFractal(ns.eval())
I had the same problem. You have to run the TensorFlow example in Jupyter notebook:
http://jupyter.org/
If you run it from other IDEs like (Spyder) all you will see is <IPython.core.display.Image object> in the console.
emmm，I have destroy this problem,you can take a look on my function:
def displayFractal(a,fmt='jpeg'):
a_cyclic=(6.28*a/200.0).reshape(list(a.shape)+[1])
# emmm I have changed the number. you can just continue your number
img=np.concatenate([5+10*np.cos(a_cyclic),15+25*np.sin(a_cyclic),70-40*np.cos(a_cyclic)],2)
img[a==a.max()]=0
a=img
a=np.uint8(np.clip(a,0,255))
plt.imshow(PIL.Image.fromarray(a))
plt.show()
of course you should import matplotlib .pyplot as plt at first.
I am trying to plot a very big file (~5 GB) using python and matplotlib. I am able to load the whole file in memory (the total available in the machine is 16 GB) but when I plot it using simple imshow I get a segmentation fault. This is most probable to the ulimit which I have set to 15000 but I cannot set higher. I have come to the conclusion that I need to plot my array in batches and therefore made a simple code to do that. My main isue is that when I plot a batch of the big array the x coordinates start always from 0 and there is no way I can overlay the images to create a final big one. If you have any suggestion please let me know. Also I am not able to install new packages like "Image" on this machine due to administrative rights. Here is a sample of the code that reads the first 12 lines of my array and make 3 plots.
import os
import sys
import scipy
import numpy as np
import pylab as pl
import matplotlib as mpl
import matplotlib.cm as cm
from optparse import OptionParser
from scipy import fftpack
from scipy.fftpack import *
from cmath import *
from pylab import *
import pp
import fileinput
import matplotlib.pylab as plt
import pickle
def readalllines(file1,rows,freqs):
file = open(file1,'r')
sizer = int(rows*freqs)
i = 0
q = np.zeros(sizer,'float')
for i in range(rows*freqs):
s =file.readline()
s = s.split()
#print s[4],q[i]
q[i] = float(s[4])
if i%262144 == 0:
print '\r ',int(i*100.0/(337*262144)),' percent complete',
i += 1
file.close()
return q
parser = OptionParser()
parser.add_option('-f',dest="filename",help="Read dynamic spectrum from FILE",metavar="FILE")
parser.add_option('-t',dest="dtime",help="The time integration used in seconds, default 10",default=10)
parser.add_option('-n',dest="dfreq",help="The bandwidth of each frequency channel in Hz",default=11.92092896)
parser.add_option('-w',dest="reduce",help="The chuncker divider in frequency channels, integer default 16",default=16)
(opts,args) = parser.parse_args()
rows=12
freqs = 262144
file1 = opts.filename
s = readalllines(file1,rows,freqs)
s = np.reshape(s,(rows,freqs))
s = s.T
print s.shape
#raw_input()
#s_shift = scipy.fftpack.fftshift(s)
#fig = plt.figure()
#fig.patch.set_alpha(0.0)
#axes = plt.axes()
#axes.patch.set_alpha(0.0)
###plt.ylim(0,8)
plt.ion()
i = 0
for o in range(0,rows,4):
fig = plt.figure()
#plt.clf()
plt.imshow(s[:,o:o+4],interpolation='nearest',aspect='auto', cmap=cm.gray_r, origin='lower')
if o == 0:
axis([0,rows,0,freqs])
fdf, fdff = xticks()
print fdf
xticks(fdf+o)
print xticks()
#axis([o,o+4,0,freqs])
plt.draw()
#w, h = fig.canvas.get_width_height()
#buf = np.fromstring(fig.canvas.tostring_argb(), dtype=np.uint8)
#buf.shape = (w,h,4)
#buf = np.rol(buf, 3, axis=2)
#w,h,_ = buf.shape
#img = Image.fromstring("RGBA", (w,h),buf.tostring())
#if prev:
# prev.paste(img)
# del prev
#prev = img
i += 1
pl.colorbar()
pl.show()
If you plot any array with more than ~2k pixels across something in your graphics chain will down sample the image in some way to display it on your monitor. I would recommend down sampling in a controlled way, something like
data = convert_raw_data_to_fft(args) # make sure data is row major
def ds_decimate(row,step = 100):
return row[::step]
def ds_sum(row,step):
return np.sum(row[:step*(len(row)//step)].reshape(-1,step),1)
# as per suggestion from tom10 in comments
def ds_max(row,step):
return np.max(row[:step*(len(row)//step)].reshape(-1,step),1)
data_plotable = [ds_sum(d) for d in data] # plug in which ever function you want
or interpolation.
Matplotlib is pretty memory-inefficient when plotting images. It creates several full-resolution intermediate arrays, which is probably why your program is crashing.
One solution is to downsample the image before feeding it into matplotlib, as #tcaswell suggests.
I also wrote some wrapper code to do this downsampling automatically, based on your screen resolution. It's at https://github.com/ChrisBeaumont/mpl-modest-image, if it's useful. It also has the advantage that the image is resampled on the fly, so you can still pan and zoom without sacrificing resolution where you need it.
I think you're just missing the extent=(left, right, bottom, top) keyword argument in plt.imshow.
x = np.random.randn(2, 10)
y = np.ones((4, 10))
x[0] = 0 # To make it clear which side is up, etc
y[0] = -1
plt.imshow(x, extent=(0, 10, 0, 2))
plt.imshow(y, extent=(0, 10, 2, 6))
# This is necessary, else the plot gets scaled and only shows the last array
plt.ylim(0, 6)
plt.colorbar()
plt.show()