def testing(num):
trainData = np.load("traindigitbasic.npy")
trainLabels = samples.loadLabelsFile("data/digitdata/traininglabels", num)
testData = np.load("testdigitbasic.npy")
testLabels = samples.loadLabelsFile("data/digitdata/testlabels", 1000)
validData = np.load("validationdigitbasic.npy")
validLabels = samples.loadLabelsFile("data/digitdata/validationlabels", 1000)
neural = NeuralNetworkClassifier(28 * 28, 50, 10, num, 3.5)
neural.train(trainData[:, 0:num], trainLabels, 100)
print "Test Data"
guess = neural.classify(testData)
samples.verify(neural, guess, testLabels)
print "==================================="
print "Validation Data"
guess = neural.classify(validData)
samples.verify(neural, guess, validLabels)
def testing(num):
trainData = np.load("trainfacebasic.npy")
trainLabels = samples.loadLabelsFile("data/facedata/facedatatrainlabels", num)
testData = np.load("testfacebasic.npy")
testLabels = samples.loadLabelsFile("data/facedata/facedatatestlabels", 151)
validData = np.load("validationfacebasic.npy")
validLabels = samples.loadLabelsFile("data/facedata/facedatavalidationlabels", 301)
loop=True
while loop:
neural = NeuralNetworkClassifier(60 * 70, 500, 1, num, 0.03)
neural.train(trainData[:,0:num], trainLabels, 100)
print "Test Data"
guess = neural.classify(testData)
loop=samples.verify(neural, guess, testLabels)
if loop:
continue
print "==================================="
print "Validation Data"
guess = neural.classify(validData)
samples.verify(neural, guess, validLabels)
def testing(num):
trainData = np.load("traindigitbasic.npy")
trainLabels = samples.loadLabelsFile("data/digitdata/traininglabels", num)
testData = np.load("testdigitbasic.npy")
testLabels = samples.loadLabelsFile("data/digitdata/testlabels", 1000)
validData = np.load("validationdigitbasic.npy")
validLabels = samples.loadLabelsFile("data/digitdata/validationlabels",
1000)
neural = NeuralNetworkClassifier(28 * 28, 50, 10, num, 3.5)
neural.train(trainData[:, 0:num], trainLabels, 100)
print "*************Test Data*************"
guess = neural.classify(testData)
samples.verify(neural, guess, testLabels)
print "***********************************"
print "************Valid Data*************"
guess = neural.classify(validData)
samples.verify(neural, guess, validLabels)
def testing(num):
trainData = np.load("trainfaceadvanced.npy")
trainLabels = samples.loadLabelsFile("data/facedata/facedatatrainlabels", num)
testData = np.load("testfaceadvanced.npy")
testLabels = samples.loadLabelsFile("data/facedata/facedatatestlabels", 151)
validData = np.load("validationfaceadvanced.npy")
validLabels = samples.loadLabelsFile("data/facedata/facedatavalidationlabels", 301)
loop=True
while loop:
neural = NeuralNetworkClassifier(60 * (70+1), 500, 1, num, 0.03)
neural.train(trainData[:,0:num], trainLabels, 100)
print "Test Data"
guess = neural.classify(testData)
loop=samples.verify(neural, guess, testLabels)
if loop:
continue
print "==================================="
print "Validation Data"
guess = neural.classify(validData)
samples.verify(neural, guess, validLabels)
def main():
"""
0: trainingData
1: solution forward output | 0
2: trainingLabel
3: initialW
4: initialb
5: solutionW
6: solutionb
"""
f = open('testData.np', 'rb')
testData = cPickle.load(f)
f.close()
hwInst = TestClassifier(range(10), 'hwCls', 123)
hwInst.initializeWeight(testData[0][0].shape[0], 10)
hwInst.W = testData[0][3]
hwInst.b = testData[0][4]
netOut = hwInst.forwardPropagation(testData[0][0])
if type(netOut) != np.ndarray:
test(False, "hand-written, 450, forward, invalid return type")
flag1 = (np.max(np.fabs(netOut - testData[0][1])) < EPSILON)
test(flag1, "hand-written, 450, forward")
hwInst.backwardPropagation(testData[0][1], testData[0][2], 0.02 / 450.)
if type(hwInst.W) != list:
test(False, "hand-written, 450, backward, invalid return type")
if type(hwInst.b) != list:
test(False, "hand-written, 450, backward, invalid return type")
for i, w in enumerate(hwInst.W):
if type(w) != np.ndarray:
test(False, "hand-written, 450, backward, invalid return type")
flag1 = (np.max(np.fabs(w - testData[0][5][i])) < EPSILON)
test(flag1, "hand-written, 450, backward, W, " + str(i))
for i, b in enumerate(hwInst.b):
if type(b) != np.ndarray:
test(False, "hand-written, 450, backward, invalid return type")
flag1 = (np.max(np.fabs(b - testData[0][6][i])) < EPSILON)
test(flag1, "hand-written, 450, backward, b, " + str(i))
hwInst = TestClassifier(range(10), 'hwCls', 123)
hwInst.initializeWeight(testData[1][0].shape[0], 10)
hwInst.W = testData[1][3]
hwInst.b = testData[1][4]
hwInst.nLayer = len(hwInst.W)
netOut = hwInst.forwardPropagation(testData[1][0])
if type(netOut) != np.ndarray:
test(False, "hand-written, 1500, forward, invalid return type")
flag1 = (np.max(np.fabs(netOut - testData[1][1])) < EPSILON)
test(flag1, "hand-written, 1500, forward")
hwInst.backwardPropagation(testData[1][1], testData[1][2], 0.02 / 1500.)
if type(hwInst.W) != list:
test(False, "hand-written, 1500, backward, invalid return type")
if type(hwInst.b) != list:
test(False, "hand-written, 1500, backward, invalid return type")
for i, w in enumerate(hwInst.W):
if type(w) != np.ndarray:
test(False, "hand-written, 1500, backward, invalid return type")
flag1 = (np.max(np.fabs(w - testData[1][5][i])) < EPSILON)
test(flag1, "hand-written, 1500, backward, W, " + str(i))
for i, b in enumerate(hwInst.b):
if type(b) != np.ndarray:
test(False, "hand-written, 1500, backward, invalid return type")
flag1 = (np.max(np.fabs(b - testData[1][6][i])) < EPSILON)
test(flag1, "hand-written, 1500, backward, b, " + str(i))
hwInst = TestClassifier(range(2), 'hwCls', 123)
hwInst.initializeWeight(testData[2][0].shape[0], 2)
hwInst.W = testData[2][3]
hwInst.b = testData[2][4]
hwInst.nLayer = len(hwInst.W)
netOut = hwInst.forwardPropagation(testData[2][0])
if type(netOut) != np.ndarray:
test(False, "faces, 450, forward, invalid return type")
flag1 = (np.max(np.fabs(netOut - testData[2][1])) < EPSILON)
test(flag1, "faces, 450, forward")
hwInst.backwardPropagation(testData[2][1], testData[2][2], 0.02 / 450.)
if type(hwInst.W) != list:
test(False, "faces, 450, backward, invalid return type")
if type(hwInst.b) != list:
test(False, "faces, 450, backward, invalid return type")
for i, w in enumerate(hwInst.W):
if type(w) != np.ndarray:
test(False, "faces, 450, backward, invalid return type")
flag1 = (np.max(np.fabs(w - testData[2][5][i])) < EPSILON)
test(flag1, "faces, 450, backward, W, " + str(i))
for i, b in enumerate(hwInst.b):
if type(b) != np.ndarray:
test(False, "faces, 450, backward, invalid return type")
flag1 = (np.max(np.fabs(b - testData[2][6][i])) < EPSILON)
test(flag1, "faces, 450, backward, b, " + str(i))
