def forwardBackward(xi, x, y, MT, time_queue, good_queue, DELTA_queue): A = neural_forward(xi, x, MT) check = argmax(A[-xi[-1]:]) # send back some progress statistic if y[check]-1 == 0: good = good_queue.get() good += 1 good_queue.put(good) good_queue.task_done() time = time_queue.get() time += 1 time_queue.put(time) time_queue.task_done() DELTA = DELTA_queue.get() DELTA = DELTA + back_propagation(y, A, MT, xi) DELTA_queue.put(DELTA) DELTA_queue.task_done()
def start(self):
'''start learning process for zone2 of facial keypoints analysis'''
while False:
self.data = self.zone2queue.get()
self.zone2queue.task_done()
self.x = self.data[:,0]
self.y = self.data[:,1]
self.A = neural_forward(self.xi, self.x, self.MT)
self.DELTA = back_propagation(self.y, self.A, self.MT, self.xi)
self.errors = sqrt((self.A[-self.xi[1]:]-self.y)**2)
self.MT = self.MT - self.alpha*self.DELTA - self.beta*self.MT
self.DELTA = 0*self.DELTA
if self.counter == self.save_when:
savetxt(self.file_out, self.MT, delimiter=',')
print 'saved zone2 data to ' + self.file_out + '\t',
print 'errors zone2: ' + str(sum(self.errors)) + '\tmax error arg: ' + str(argmax(self.errors)) + '\t MEAE Z2: ' + str(int(amax(self.errors))) + '\tmin error arg: ' + str(argmin(self.errors)) + '\t MinEAE Z2: ' + str(int(amin(self.errors)))
self.counter = 0 # reset
self.counter += 1
from numpy import *
from PIL import Image, ImageDraw
from neural_forward import *
MTA = genfromtxt('MT_zoneA_backup.csv', delimiter=',')
MTB = genfromtxt('MT_zoneB_backup.csv', delimiter=',')
data = genfromtxt('mini_mini_training.csv', delimiter=',')
data = data[0:10,30:]/255.
dims = shape(data)
xi1 = [96*96, 30]
xi2 = [30, 30]
counter=0
for eachline in range(0,dims[0]):
x = data[eachline,:]
A = neural_forward(xi1, x, MTA)[-30:]
B = neural_forward(xi2, A, MTB)[-30:]*96.
im = x.reshape((96,96))*255.0
im = Image.fromarray(im).convert('RGB')
nums = [2*j for j in range(0,15)]
#draw = ImageDraw.Draw(im)
#for i in nums:
# xcoord = B[i]
# ycoord = B[i+1]
# print str(xcoord)+', '+str(ycoord)
# draw.ellipse((xcoord-1,ycoord-1,xcoord+1,ycoord+1), fill='red', outline='red')
imstring = 'fk_'+str(eachline)+'.png'
im.save(imstring)
#
from numpy import *
from neural_forward import *
data = genfromtxt('test.csv', delimiter =',')[:,1:]/255.
dims = shape(data)
MTZ1 = genfromtxt('MT_zoneA.csv', delimiter=',')
MTZ2 = genfromtxt('MT_zoneB.csv', delimiter=',')
lookup_table = open('IdLookupTable.csv', 'rb')
xi1 = [96*96, 30]
xi2 = [30, 30]
headings = ['left_eye_center_x','left_eye_center_y','right_eye_center_x','right_eye_center_y','left_eye_inner_corner_x','left_eye_inner_corner_y','left_eye_outer_corner_x','left_eye_outer_corner_y','right_eye_inner_corner_x','right_eye_inner_corner_y','right_eye_outer_corner_x','right_eye_outer_corner_y','left_eyebrow_inner_end_x','left_eyebrow_inner_end_y','left_eyebrow_outer_end_x','left_eyebrow_outer_end_y','right_eyebrow_inner_end_x','right_eyebrow_inner_end_y','right_eyebrow_outer_end_x','right_eyebrow_outer_end_y','nose_tip_x','nose_tip_y','mouth_left_corner_x','mouth_left_corner_y','mouth_right_corner_x','mouth_right_corner_y','mouth_center_top_lip_x','mouth_center_top_lip_y','mouth_center_bottom_lip_x','mouth_center_bottom_lip_y']
print 'RowId,Location'
for i in range(0,dims[0]):
x = data[i,:]
z1out = neural_forward(xi1, x, MTZ1)
z2in = z1out[-30:]
results = neural_forward(xi2, z2in, MTZ2)[-30:]
lookup_iterator = open('IdLookupTable.csv', 'rb')
for eachline in lookup_iterator:
values = eachline.split(',')
row_id = int(values[0])
image_id = int(values[1])
feature_name = values[2].rstrip('\r\n')
if image_id == i+1:
get_value = headings.index(feature_name)
print str(row_id) + ',' + str(96*results[get_value])
