I am learning Theano to accelerate my image processing functions. As a start, I am trying to reimplement the function to turn images from colors to black and white (with the same number of channels): http://www.marcogiordanotd.com/blog/python/image-processing-pycuda . The author wants to show how efficient it is to do it using CUDA.
I want to do the same using OpenCL and an AMDGPU. My installation worked fine and I passed the test from http://deeplearning.net/software/theano/tutorial/using_gpu.html# successfully.
However I am dumbfunded by the result: my numpy implementation of the black and white function is faster than Theano's. Note I couldn't help but vectorizing the "blackWhite" function from above-mentioned author: he was using for loops to do matrix calculations...
my code is as follows, if you want to test it you need to change inPath to the path of a colorful image under if __name__=='__main__':
from PIL import Image
import time
import os
#import pycuda.driver as cuda
#import pycuda.autoinit
#from pycuda.compiler import SourceModule
from theano import function, config, shared, tensor
import numpy as np
#
def blackWhite(inPath , outPath , mode = "luminosity",log = 0):
if log == 1 :
print ("----------> SERIAL CONVERSION")
totalT0 = time.time()
im = Image.open(inPath)
px = np.array(im)
getDataT1 = time.time()
print ("-----> Opening path :" , inPath)
processT0 = time.time()
if mode == 'luminosity':
px=np.rollaxis(np.tile(np.dot(px,(0.21,0.71,0.07)).astype('uint8'),(3,1,1)),0,3)
else:
px=np.rollaxis(np.tile(np.dot(px,(1/3,1/3,1/3)).astype('uint8'),(3,1,1)),0,3)
processT1= time.time()
#px = np.array(im.getdata())
im = Image.fromarray(px)
im.save(outPath)
print ("-----> Saving path :" , outPath)
totalT1 = time.time()
if log == 1 :
print ("Image size : ",im.size)
print ("get and convert Image data : " ,getDataT1-totalT0 )
print ("Processing data : " , processT1 - processT0 )
print ("Save image time : " , totalT1-processT1)
print ("total Execution time : " ,totalT1-totalT0 )
print ("\n")
def TheanoBlackWhite(inPath, outPath, mode = "luminosity" , log = 0):
if log == 1 :
print ("----------> THEANO CONVERSION")
totalT0 = time.time()
im = Image.open(inPath)
px = np.array(im)
getDataT1 = time.time()
print ("-----> Opening path :" , inPath)
processT0 = time.time()
x = shared(px)
if mode == 'luminosity':
weights = shared(np.array([0.21,0.71,0.07]))
else:
weights = shared(np.array([1/3,1/3,1/3]))
f = function([], tensor.tile(tensor.dot(x,weights),(3,1,1)).dimshuffle((1,2,0)))
px=f()
processT1= time.time()
im = Image.fromarray(px.astype('uint8'))
im.save(outPath)
print ("-----> Saving path :" , outPath)
totalT1 = time.time()
if np.any([isinstance(x.op, tensor.Elemwise) and
('Gpu' not in type(x.op).__name__)
for x in f.maker.fgraph.toposort()]):
print('Used the cpu')
else:
print('Used the gpu')
if log == 1 :
print ("Image size : ",im.size)
print ("get and convert Image data : " ,getDataT1-totalT0 )
print ("Processing data : " , processT1 - processT0 )
print ("Save image time : " , totalT1-processT1)
print ("total Execution time : " ,totalT1-totalT0 )
print ("\n")
if __name__=='__main__':
lim = os.listdir(path=r'./train_sample')
inPath = os.path.join(r'./train_sample',lim[0])#just first image
blackWhite(inPath, 'out_np.jpg', mode = "luminosity" , log = 1)
TheanoBlackWhite(inPath, 'out_theano.jpg', mode = "luminosity" , log = 1)
result:
----------> SERIAL CONVERSION
-----> Opening path : ./train_sample/e04e300c909046d8.jpg
-----> Saving path : out_np.jpg
Image size : (1600, 1200)
get and convert Image data : 0.03160548210144043
Processing data : 0.06990170478820801
Save image time : 0.08301019668579102
total Execution time : 0.18471074104309082
----------> THEANO CONVERSION
-----> Opening path : ./train_sample/e04e300c909046d8.jpg
-----> Saving path : out_theano.jpg
Used the cpu
Image size : (1600, 1200)
get and convert Image data : 0.03149127960205078
Processing data : 0.13131022453308105
Save image time : 0.06376218795776367
total Execution time : 0.2267618179321289
