def checkAllPeople(config, color="#ab1749"):
from sklearn.model_selection import train_test_split
import numpy as np
model = DatasetModel([config[0], config[1]])
model = model.labeledByFolderOfFiles(config[2])
m, n = model.getDim()
X, y = model.exportedAsClassicDataset()
pI = model.partitionIndexes
X0 = X[:pI[1]]
y0 = y[:pI[1]]
X_train, X_test1, y_train, y_test1 = train_test_split(
X0,
y0,
test_size=0.2, # 0.2
random_state=0,
stratify=y0)
X_test2 = X[pI[1]:]
y_test2 = y[pI[1]:]
print(X_test1.shape, X_test2.shape)
X_test = np.concatenate((X_test1, X_test2))
y_test = np.concatenate((y_test1, y_test2))
eigenfaceModel = EigenfaceModel(X_train,
y_train,
nmin=4,
nmax=150,
m=m,
n=n)
epsilons = zeros(len(y_test))
for i, X_i in enumerate(X_test):
Phi_i = X_i - eigenfaceModel.mean_face
Ω_i = eigenfaceModel.projectOntoFacespace(X_i)
epsilons[i] = sqrt(abs(Phi_i.T.dot(Phi_i) -
Ω_i.T.dot(Ω_i))) #sqrt(norm(X_i - Ω_i))
# 4 possibilities (from paper)
# (1) near face space and near a face class
# (2) near face space but not near to a known face class
# (3) distant from face space and near a face class
# (4) distant from face space and not near a known face class
plotHist(epsilons, "Distance between image and face-space",
"Distance Hist for faces that should be known", color)
print(max(epsilons))
sd = np.std(epsilons, ddof=1, dtype=np.float64)
mean = np.mean(epsilons)
print("mean:", mean)
print("sd:", sd)
print("suggested cut threshold (mean+2sd):", mean + 2 * sd)
return X_train, y_train, X_test, y_test, eigenfaceModel, model
def showMinDistancesBetweenInVsOutTrainingDataset(config):
from sklearn.model_selection import train_test_split
import numpy as np
model = DatasetModel([config[0], config[1]])
model = model.labeledByFolderOfFiles(config[2])
m, n = model.getDim()
X, y = model.exportedAsClassicDataset()
pI = model.partitionIndexes
X0 = X[:pI[1]]
y0 = y[:pI[1]]
X_train, X_test1, y_train, y_test1 = train_test_split(
X0,
y0,
test_size=0.2, # 0.2
random_state=0,
stratify=y0)
X_test2 = X[pI[1]:]
y_test2 = y[pI[1]:]
eigenfaceModel = EigenfaceModel(X_train,
y_train,
nmin=4,
nmax=150,
m=m,
n=n) # 4 | 150
# People that should be KNOWN
epsilons1 = zeros(len(y_test1))
for i, X_i in enumerate(X_test1):
y_pred_i, min_err_i = eigenfaceModel._noFitTest(X_i)
epsilons1[i] = min_err_i
# People that should NOT be KNOWN
epsilons2 = zeros(len(y_test2))
for i, X_i in enumerate(X_test2):
y_pred_i, min_err_i = eigenfaceModel._noFitTest(X_i)
epsilons2[i] = min_err_i
plotHist(epsilons1, "Minimum error vs other samples",
"(min) Error Hist for faces that should be known", blue_color)
sd, mean = np.std(epsilons1, ddof=1, dtype=np.float64), np.mean(epsilons1)
print("mean:", mean, " | sd:", sd, " |max:", max(epsilons1))
print("suggested cut threshold (mean+2sd):", mean + 2 * sd)
plotHist(epsilons2, "Minimum error vs other samples",
"(min) Error Hist for faces that should NOT be known", pink_color)
sd, mean = np.std(epsilons2, ddof=1, dtype=np.float64), np.mean(epsilons2)
print("mean:", mean, " | sd:", sd, " |max:", max(epsilons2))
print("suggested cut threshold (mean+2sd):", mean + 2 * sd)
def checkUnknownPeople(config, color=pink_color):
model = DatasetModel([config[0], config[1]])
model = model.labeledByFolderOfFiles(config[2])
m, n = model.getDim()
X, y = model.exportedAsClassicDataset()
pI = model.partitionIndexes
X_train = X[:pI[1]]
y_train = y[:pI[1]]
X_test = X[pI[1]:]
y_test = y[pI[1]:]
eigenfaceModel = EigenfaceModel(X_train,
y_train,
nmin=4,
nmax=150,
m=m,
n=n)
epsilons = zeros(len(y_test))
for i, X_i in enumerate(X_test):
Phi_i = X_i - eigenfaceModel.mean_face
Ω_i = eigenfaceModel.projectOntoFacespace(X_i)
#Phi_f = zeros(len(Phi_i))
#Phi_f[:len(Ω_i)] = Ω_i
#epsilons[i] = norm(Phi_i - Phi_f)
epsilons[i] = sqrt(abs(Phi_i.T.dot(Phi_i) -
Ω_i.T.dot(Ω_i))) #sqrt(norm(X_i - Ω_i))
#print(argmax(epsilons))
#print(model.files[argmax(epsilons)])
# 4 possibilities (from paper)
# (1) near face space and near a face class
# (2) near face space but not near to a known face class
# (3) distant from face space and near a face class
# (4) distant from face space and not near a known face class
plotHist(epsilons, "Distance between image and face-space",
"Distance Hist for faces that should NOT be known", color)
print(max(epsilons))
return X_train, y_train, X_test, y_test, eigenfaceModel, model
# Let's do a second split between just known people (to mix later)
X_train, X_test1, y_train, y_test1 = train_test_split(
X0,
y0,
test_size=0.2, # 0.2
random_state=0,
stratify=y0)
# Unknown people
X_test2 = X[pI[1]:]
y_test2 = y[pI[1]:]
eigenfaceModel = EigenfaceModel(X_train,
y_train,
nmin=4,
nmax=150,
m=m,
n=n)
print(eigenfaceModel)
X_test = np.concatenate((X_test1, X_test2))
y_test = np.concatenate((y_test1, y_test2))
# People that should be KNOWN
#epsilons1 = zeros(len(y_test1))
#for i, X_i in enumerate(X_test1):
# y_pred_i, min_err_i = eigenfaceModel._noFitTest(X_i)
# epsilons1[i] = min_err_i
# People that should NOT be KNOWN
#epsilons2 = zeros(len(y_test2))
model = model.labeledByFolderOfFiles(output100strict_classes)
X, y = model.exportedAsClassicDataset()
#X_train, X_test, y_train, y_test = train_test_split(X,
# y,
# test_size=0.1, # 0.2
# random_state=0,
# stratify=y)
pI = model.partitionIndexes
X_train = X[:pI[1]]
y_train = y[:pI[1]]
X_test = X[pI[1]:]
y_test = y[pI[1]:]
eigenfaceModel = EigenfaceModel(X_train, y_train, nmin=2, nmax=50)
err = zeros(len(y_test))
for i, X_i in enumerate(X_test):
y_i, err[i] = eigenfaceModel._noFitTest(X_i)
plotHist(
err, 'Error',
'Errors Histogram for faces that should be KNOWN from the model')
print(err)
print(max(err))
if 0:
###########################################################################
#2.
model = DatasetModel([output100lbp, output100lbp_test_complement])
X, y = model.exportedAsClassicDataset()
indices = range(len(y))
X_train, X_test, y_train, y_test, i_train, i_test = train_test_split(
X,
y,
indices,
test_size=0.1, # 0.2
random_state=0,
stratify=y)
#X_test = X_test[y_test < output100_all_classes.index('io')]
#y_test = y_test[y_test < output100_all_classes.index('io')]
eigenfaceModel = EigenfaceModel(
X_train, y_train, nmin=2,
nmax=150) # old config 2 | 150 (documentation)
print(eigenfaceModel)
y_predict2 = zeros(len(y_test))
for i, X_i in enumerate(X_test):
y_predict2[i] = eigenfaceModel.noFitTest(X_i, 1)
from sklearn.metrics import classification_report
import matplotlib.pyplot as plt
print(classification_report(y_test, y_predict2, target_names=labels))
plotConfusionMatrix(y_test, y_predict2, labels=labels)
# ---------------------- ANGLE ----------------------------------------