I want to build Voice command project by using RPi and python. I use MFCC and fastDTW to match that voice but I got this error and I have no idea how to fix it. Here the code...
def fastdtw(x, y, radius=1, dist=lambda a, b: abs(a - b)):
min_time_size = radius + 2
if len(x) < min_time_size or len(y) < min_time_size:
return dtw(x, y, window = None, dist=dist)
x_shrinked = __reduce_by_half(x)
y_shrinked = __reduce_by_half(y)
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
window = __expand_window(path, len(x), len(y), radius)
return dtw(x, y, window, dist=dist)
def dtw(x, y, window=None, dist=lambda a, b: abs(a - b)):
len_x, len_y = len(x), len(y)
if window is None:
window = [(i, j) for i in xrange(len_x) for j in xrange(len_y)]
window = [(i + 1, j + 1) for i, j in window]
D = np.full((len_x+1, len_y+1), np.inf, dtype=('f4, i4, i4'))
D[0, 0] = (0, 0, 0)
for i, j in window:
D[i, j] = min((D[i-1, j][0], i-1, j), (D[i, j-1][0], i, j-1), (D[i-1, j-1][0], i-1, j-1), key=lambda a: a[0])
D[i, j][0] += dist(x[i-1], y[j-1])
path = []
i, j = len_x, len_y
while not (i == j == 0):
path.append((i-1, j-1))
i, j = D[i, j][1], D[i, j][2]
path.reverse()
return (D[len_x, len_y][0], path)
Run file:
from __future__ import absolute_import, division, print_function, unicode_literals
from features import mfcc
from features import logfbank
import scipy.io.wavfile as wav
import time
from numpy.linalg import norm
import unittest
import numpy as np
from fastdtw import fastdtw, dtw
import bisect
from six.moves import xrange
from collections import defaultdict
start = time.time()
(rate1,sig1) = wav.read("/home/pi/OpenCalculator.wav")
(rate2,sig2) = wav.read("/home/pi/voiceCommand.wav")
mfcc1 = mfcc(sig1,rate1)
mfcc2 = mfcc(sig2,rate2)
dist, path = fastdtw(mfcc1, mfcc2)
elapsed = time.time()-start
And this is error message:
Traceback (most recent call last):
File "/home/pi/test.py", line 23, in <module>
dist, path = fastdtw(mfcc1, mfcc2)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 20, in fastdtw
distance, path = fastdtw(x_shrinked, y_shrinked, radius=radius, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 16, in fastdtw
return dtw(x, y, window = None, dist=dist)
File "build/bdist.linux-armv7l/egg/fastdtw.py", line 34, in dtw
D[i, j][0] += dist(x[i-1], y[j-1])
ValueError: setting an array element with a sequence.
*** output of mccc is in numpy array form.
Please help....
You need to redefine distance to work with feature vectors instead of numbers (default distance works with numbers, not with vectors):
def mfcc_dist(a,b):
dist = 0
for x, y in zip(a,b):
dist = dist + (x - y) * (x - y)
return sqrt(dist)
dist, path = fastdtw(mfcc1, mfcc2, dist=mfcc_dist)
You can also use numpy.linalg.norm(a-b).
mfcc1 and mfcc2 should be list or numpy array. Do they have correct type?
Related
I'm have been working with SMAP data satellite, specially for moisture and soil proporties.
I follow the idea of use GDAL solve everything, and make something similar to this published in Link to first approach to download SMAP data
Modifing the code and testing:
import os
import h5py
import numpy as np
from osgeo import gdal, gdal_array, osr
# the file to download
https://n5eil01u.ecs.nsidc.org/SMAP/SPL4SMAU.003/2017.08.01/SMAP_L4_SM_aup_20170801T030000_Vv3030_001.h5
path = "/path/to/data"
h5File = h5py.File(path + "SMAP_L4_SM_aup_20170801T030000_Vv3030_001.h5", 'r')
data = h5File.get('Analysis_Data/sm_rootzone_analysis')
lat = h5File.get("cell_lat")
lon = h5File.get("cell_lon")
np_data = np.array(data)
np_lat = np.array(lat)
np_lon = np.array(lon)
num_cols = float(np_data.shape[1])
num_rows = float(np_data.shape[0])
xmin = np_lon.min()
xmax = np_lon.max()
ymin = np_lat.min()
ymax = np_lat.max()
xres = (xmax - xmin) / num_cols
yres = (ymax - ymin) / num_rows
nrows, ncols = np_data.shape
xres = (xmax - xmin) / float(ncols)
yres = (ymax - ymin) / float(nrows)
geotransform = (xmin, xres, 0, ymax, 0, -xres)
dataFileOutput = path + "sm_rootzone_analysis.tif"
output_raster = gdal.GetDriverByName('GTiff').Create(dataFileOutput, ncols, nrows, 1, gdal.GDT_Float32) # Open the file
output_raster.SetGeoTransform(geotransform)
srs = osr.SpatialReference()
srs.ImportFromEPSG(4326)
output_raster.SetProjection(srs.ExportToWkt())
output_raster.GetRasterBand(1).WriteArray(np_data) # Writes my array to the raster
del output_raster
So, using this approach, the result is a global map with many problems of projections, as for example the image below, produced by the python code above.
To compare with a correct data, the same image was extract from h5, using HEG nasa software.
If the data is really in the EASE2 Global grid, you shouldn't assign EPSG:4326 as a the coordinate system with lat/lon degrees in the geotransform.
If you convert the lat/lon coordinates to the EASE2 Grid at 9km, your geotransform should be something like:
geotransform = (-17367530.44516138, 9000, 0, 7314540.79258289, 0, -9000.0)
and the srs:
srs.ImportFromEPSG(6933)
I copy a code from a Web page to Python 2.7 but I didn't success.
The code is:
# Raspbery Pi Color Tracking Project
# Code written by Oscar Liang
# 30 Jun 2013
import cv2.cv as cv
import smbus
bus = smbus.SMBus(1)
address = 0x04
def sendData(value):
bus.write_byte(address, value)
# bus.write_byte_data(address, 0, value)
return -1
def readData():
state = bus.read_byte(address)
# number = bus.read_byte_data(address, 1)
return state
def ColorProcess(img):
# returns thresholded image
imgHSV = cv.CreateImage(cv.GetSize(img), 8, 3)
# converts BGR image to HSV
cv.CvtColor(img, imgHSV, cv.CV_BGR2HSV)
imgProcessed = cv.CreateImage(cv.GetSize(img), 8, 1)
# converts the pixel values lying within the range to 255 and stores it in the destination
cv.InRangeS(imgHSV, (100, 94, 84), (109, 171, 143), imgProcessed)
return imgProcessed
def main():
# captured image size, change to whatever you want
width = 320
height = 240
capture = cv.CreateCameraCapture(0)
# Over-write default captured image size
cv.SetCaptureProperty(capture,cv.CV_CAP_PROP_FRAME_WIDTH,width)
cv.SetCaptureProperty(capture,cv.CV_CAP_PROP_FRAME_HEIGHT,height)
cv.NamedWindow( “output”, 1 )
cv.NamedWindow( “processed”, 1 )
while True:
frame = cv.QueryFrame(capture)
cv.Smooth(frame, frame, cv.CV_BLUR, 3)
imgColorProcessed = ColorProcess(frame)
mat = cv.GetMat(imgColorProcessed)
# Calculating the moments
moments = cv.Moments(mat, 0)
area = cv.GetCentralMoment(moments, 0, 0)
moment10 = cv.GetSpatialMoment(moments, 1, 0)
moment01 = cv.GetSpatialMoment(moments, 0,1)
# Finding a big enough blob
if(area > 60000):
# Calculating the center postition of the blob
posX = int(moment10 / area)
posY = int(moment01 / area)
# check slave status and send coordinates
state = readData()
if state == 1:
sendData(posX)
sendData(posY)
print ‘x: ‘ + str(posX) + ‘ y: ‘ + str(posY)
# update video windows
cv.ShowImage(“processed”, imgColorProcessed)
cv.ShowImage(“output”, frame)
if cv.WaitKey(10) >= 0:
break
return;
if __name__ == “__main__”:
main()
I solved it. The right code is:
import cv2.cv as cv
import smbus
import cv2
bus = smbus.SMBus(1)
address = 0x04
def sendData(value):
bus.write_byte(address, value)
return -1
def readData():
state = bus.read_byte(address)
return state
def ColorProcess(img):
imgHSV = cv.CreateImage(cv.GetSize(img) ,8 ,3)
cv.CvtColor(img, imgHSV, cv.CV_BGR2HSV)
imgProcessed = cv.CreateImage(cv.GetSize(img) ,8 ,1)
cv.InRangeS(imgHSV, (100, 94, 84), (109, 171, 143), imgProcessed)
return imgProcessed
def main():
width = 320
height = 240
capture = cv.CreateCameraCapture(0)
cv.SetCaptureProperty(capture, cv.CV_CAP_PROP_FRAME_WIDTH, width)
cv.SetCaptureProperty(capture, cv.CV_CAP_PROP_FRAME_HEIGHT, height)
cv.NamedWindow("output", 1)
cv.NamedWindow("processed", 1)
while True:
frame = cv.QueryFrame(capture)
cv.Smooth(frame, frame, cv.CV_BLUR, 3)
imgColorProcessed = ColorProcess(frame)
mat = cv.GetMat(imgColorProcessed)
moments = cv.Moments(mat, 0)
area = cv.GetCentralMoment(moments, 0, 0)
moment10 = cv.GetSpatialMoment(moments, 1, 0)
moment01 = cv.GetSpatialMoment(moments, 0, 1)
if (area > 60000):
posX = int(moment10/area)
posY = int(moment01/area)
ali = long(2000000)
state = readData()
if state == 1:
sendData(posX)
sendData(posY)
print 'x: ' + str(posX) + 'y: ' + str(posY)
cv.ShowImage("processed", imgColorProcessed)
cv.ShowImage("output", frame)
if cv.WaitKey(10) >= 0:
break
return;
if __name__ == "__main__":
main()
I have the code below and I want to modify it in many parts :
how can I use Raspbery Pi camera instead USB camera?
I will be grateful for anyone who gives me a hint or write the right code.
The code is :
import cv2.cv as cv
import smbus
import cv2
bus = smbus.SMBus(1)
address = 0x04
def sendData(value):
bus.write_byte(address, value)
return -1
def readData():
state = bus.read_byte(address)
return state
def ColorProcess(img):
imgHSV = cv.CreateImage(cv.GetSize(img) ,8 ,3)
cv.CvtColor(img, imgHSV, cv.CV_BGR2HSV)
imgProcessed = cv.CreateImage(cv.GetSize(img) ,8 ,1)
cv.InRangeS(imgHSV, (100, 94, 84), (109, 171, 143), imgProcessed)
return imgProcessed
def main():
width = 320
height = 240
capture = cv.CreateCameraCapture(0)
cv.SetCaptureProperty(capture, cv.CV_CAP_PROP_FRAME_WIDTH, width)
cv.SetCaptureProperty(capture, cv.CV_CAP_PROP_FRAME_HEIGHT, height)
cv.NamedWindow("output", 1)
cv.NamedWindow("processed", 1)
while True:
frame = cv.QueryFrame(capture)
cv.Smooth(frame, frame, cv.CV_BLUR, 3)
imgColorProcessed = ColorProcess(frame)
mat = cv.GetMat(imgColorProcessed)
moments = cv.Moments(mat, 0)
area = cv.GetCentralMoment(moments, 0, 0)
moment10 = cv.GetSpatialMoment(moments, 1, 0)
moment01 = cv.GetSpatialMoment(moments, 0, 1)
if (area > 60000):
posX = int(moment10/area)
posY = int(moment01/area)
ali = long(2000000)
state = readData()
if state == 1:
sendData(posX)
sendData(posY)
print 'x: ' + str(posX) + 'y: ' + str(posY)
cv.ShowImage("processed", imgColorProcessed)
cv.ShowImage("output", frame)
if cv.WaitKey(10) >= 0:
break
return;
if __name__ == "__main__":
main()
I will high appreciate any help.
Thanks.
Run this command in LX Terminal in Pi.It will take care of drivers.
sudo modprobe bcm2835-v4l2
I am trying to draw a legend under two plots (created using twinx). I want the legend to draw at the bottom center aligned with 4 columns. So far no success. How can I make the legend with respect to the entire plot, not just with a single axis object. Any help ?
import matplotlib.pyplot as plt;
import numpy as np;
from matplotlib import rc;
filename = 'ml.pdf';
fig, ax1 = plt.subplots(frameon=False);
rc('mathtext', default='regular');
rc('lines',lw=2.6);
rc('lines',mew=2.4);
rc('text', usetex=True);
x = np.array([5,10,20,50]);
dp_g = np.array([23.43, 29.93, 36.50, 46.07]);
mr_g = np.array([25.33, 31.83, 38.39, 47.75]);
md_g = np.array([24.94, 31.33, 37.80, 47.10]);
sb_g = np.array([27.01, 34.86, 43.18, 54.35]);
lns1 = ax1.plot(x,dp_g,'bs:', label="MD\n($\lambda$=.8)");
lns2 = ax1.plot(x,mr_g,'bs--',label="MR\n($\lambda$=.1)");
lns3 = ax1.plot(x,md_g,'bs-.',label='MD');
lns4 = ax1.plot(x,sb_g,'bs-',label="SB\n($\gamma$=.1)");
ax1.set_ylabel('CG ($\times$ 100)',color='b',size=14);
ax1.set_ylim([20,57]);
ax1.set_xlim([4,51]);
ax1.set_xticks(x);
ax1.tick_params(axis='y', which=u'both', length=0, labelsize=14, colors='b');
ax1.tick_params(axis='x', which=u'both', length=0, labelsize=14);
ax2 = ax1.twinx();
dp_d = np.array([18.84, 19.55, 20.09, 20.08]);
mr_d = np.array([19.42, 19.73, 20.06, 20.04]);
md_d = np.array([19.02, 19.75, 20.28, 20.29]);
sb_d = np.array([20.81, 19.77, 19.20, 19.03]);
lns6 = ax2.plot(x,dp_d,'rv:',label="MD\n($\lambda$=.8)");
lns7 = ax2.plot(x,mr_d,'rv--',label="MR\n($\lambda$=.1)");
lns8 = ax2.plot(x,md_d,'rv-.',label='MD');
lns9 = ax2.plot(x,sb_d,'rv-',label="SB\n($\gamma$=.1)");
lns = lns1 + lns2 + lns3 + lns4 + lns6 + lns7 + lns8 + lns9;
labs = [l.get_label() for l in lns];
ax2.set_ylabel('LD ($\times$ 100)',color='r',size=14);
ax2.set_ylim([15,23]);
ax2.set_xlim([4,51]);
ax2.set_xticks(x);
ax2.tick_params(axis='y', which=u'both', length=0, labelsize=14, colors='r');
ax2.tick_params(axis='x', which=u'both', length=0, labelsize=14);
ax1.set_xlabel('\# of items',size=14);
borderaxespad=2.5, ncol = 1, fontsize='11.5');
lgd = ax1.legend(lns, labs, bbox_to_anchor=(1.01,1.0), loc='lower center', borderaxespad=2.5, ncol = 4, fontsize='14');
fig.savefig(filename,format='pdf',transparent=True, bbox_extra_artists=(lgd,), bbox_inches='tight');
Apart from the broken line borderaxespad=2.5, ncol = 1, fontsize='11.5');, I believe what you want to do is to just remove the bbox_to_anchor=(1.01, 1.0) from the legend-definition. Doing so will put the legend at the bottom center of the plot (however the legend is very wide so it will span the entire width of the plot).
I just finished a work program to faces recognition using python on ubuntu system
But when you want to move the work to "Raspberry pi" gives this error
this is full error :
AttributeError: 'module' object has no attribute 'createLBPHFaceRecognizer'
What is the solution
Thank you
import cv2
import sys
import cv
import glob
import numpy as np
import os
labeltest=[]
Images=[]
Len=0
model = cv2.createLBPHFaceRecognizer(1,8,8,8,70.0)
Labels=[]
textsay=""
# *********** Read *****************\\
def read():
arr={}
with open("csv.ext") as f:
for line in f:
arr=line.split("%",2)
labeltest.append(arr[1])
Images.append(cv2.imread(arr[0],cv2.IMREAD_GRAYSCALE))
label=range(0,len(labeltest))
for i in range(0,len(labeltest)):
label[i]=int(labeltest[i])
print (label)
model.train(np.asarray(Images),np.asarray(label))
model.save("mezo.xml")
model.load("mezo.xml")
# //*********** Read *****************
def writetofile(key):
fo = open("csv.ext", "a+")
fo.write(key)
fo.write("\n")
def searchName(key):
lines=tuple(open("Names.txt","r"))
for i in range(0,len(lines)):
test=lines[i].split("\n")
print test[0]
if str(key.lower())==str(test[0].lower()):
return i
return -1
def readName():
lines=tuple(open("Names.txt","r"))
for i in range(0,len(lines)):
Labels.append(lines[i])
print Labels
def AddName(key):
fo = open("Names.txt", "a+")
fo.write(key)
fo.write("\n")
readName()
# *********** Add *****************\\
def Add(faces,gray):
count=Len+100
for (x, y, w, h) in faces:
filename = "/home/mohammad/Desktop/traning/%03d"%count +".pgm"
f=gray[y:y+h,x:x+w]
f=cv2.resize(f,(92,112),interpolation=cv2.INTER_LANCZOS4)
newName=raw_input("Enter the Name : ")
index=searchName(newName)
if index==-1:
index=len(Labels)
AddName(newName)
filenameIn = filename+"%"+str(index)
writetofile(filenameIn)
cv2.imwrite(filename,f)
count+=1
read()
# //*********** Add *****************
path={}
path=glob.glob("/home/mohammad/Desktop/traning/*.pgm")
Len=len(path)-1
cascPath = "haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
count=0
video_capture = cv2.VideoCapture(0)
read();
readName()
while True:
# Capture frame-by-frame
ret, frame = video_capture.read()
cv2.waitKey(10)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = faceCascade.detectMultiScale(
frame,
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30),
flags=cv2.cv.CV_HAAR_SCALE_IMAGE
)
# Draw a rectangle around the faces
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
f=gray[y:y+h,x:x+w]
f=cv2.resize(f,(92,112),interpolation=cv2.INTER_LANCZOS4)
cv2.imwrite("11.pgm",f)
label, confidence = model.predict(f)
print"Threshold : ", model.getDouble("threshold")
if label>-1:
if Labels[label] != textsay:
cmd = 'espeak "{0}" 2>/dev/null'.format(Labels[label])
os.system(cmd)
textsay=Labels[label]
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame,Labels[label],(x,y-10), font, 1.0,(255,255,255))
print "\n"+str(Labels[label])+" | "+str(confidence)
# Display the resulting frame
cv2.imshow('Video', frame)
k=cv2.waitKey(5)& 0xFF
if k==97 :
Add(faces,gray)
if k==27:
exit()