def train_classifier():
# first, load target and non-target training data
train_target = png2fea(TRAIN_TARGET) # target training data
train_ntarget = png2fea(TRAIN_NTARGET) # non-target training data
# convert the grayscale images to 1d arrays
x1 = []; x2 = []
for im in train_target.values():
x1.append(inflate_data(im))
for im in train_ntarget.values():
x2.append(inflate_data(im))
x1 = np.vstack(x1)
x2 = np.vstack(x2)
# convert data to numpy arrays
x1 = np.array(x1) # target
x2 = np.array(x2) # non-target
dim = x1.shape[1]
# standardise the data
train_mean = np.mean(np.vstack((x1, x2)), axis=0)
train_std = np.std(np.vstack((x1, x2)), axis=0)
x1 -= train_mean
x1 /= train_std
x2 -= train_mean
x2 /= train_std
cov_tot = np.cov(np.vstack([x1, x2]).T, bias=True)
# PCA - reduce the dimensionality
d_pca, e_pca = scipy.linalg.eigh(cov_tot, eigvals=(dim-150, dim-1))
x1_pca = x1.dot(e_pca)
x2_pca = x2.dot(e_pca)
# perform the LDA on the reduced data space
cov_tot_pca = np.cov(np.vstack([x1_pca, x2_pca]).T, bias=True)
dim_pca = x1_pca.shape[1]
n_x1 = len(x1_pca)
n_x2 = len(x2_pca)
cov_wc = (n_x1*np.cov(x1_pca.T, bias=True) + n_x2*np.cov(x2_pca.T, bias=True)) / (n_x1 + n_x2)
cov_ac = cov_tot_pca - cov_wc
d_lda, e_lda = scipy.linalg.eigh(cov_ac, cov_wc, eigvals=(dim_pca-1, dim_pca-1))
# now we've got our one dimensional data
x1_lda = x1_pca.dot(e_lda)
x2_lda = x2_pca.dot(e_lda)
# compute the gaussian distributions for our classes and evalueate the test data
mean_x1, cov_x1 = train_gauss(x1_lda)
mean_x2, cov_x2 = train_gauss(x2_lda)
# now save the model parameters
model_parameters = [e_pca, e_lda, (mean_x1, cov_x1), (mean_x2, cov_x2),
train_mean, train_std]
with open('img_pca_lda.model', 'wb') as f:
pickle.dump(model_parameters, f)
f.close()
def main():
# # # Getting all training data from data/train
print("STEP1: getting training and evaluation data")
toTrain = []
filenames = os.listdir(TRAIN_DIR)
for filename in filenames:
person = png2fea(TRAIN_DIR + "/" + filename).values()
CLASSES.extend(
[filename] * len(person)
) # array of names of classes corresponding with each person
toTrain.extend(person) # adding feature of one person in the arre
# # # Getting all evaluation data from data/evaluate
toEvaluate = []
toEvalNames = []
evaluateDict = png2fea(EVAL_DIR)
toEvalNames.extend(evaluateDict.keys())
temp = evaluateDict.values()
toEvaluate.extend(temp)
print("STEP1 done.")
toTrain_2d, toEvaluate_2d = imagesModify(toTrain, toEvaluate)
pca = performPCA(toTrain_2d)
# To see the graph of PCA and all eigenfaces, set this variable to 1
showPCAandEigenss = 0
if (showPCAandEigenss == 1):
showPCAandEigens(pca)
eigenfaces = pca.components_.reshape((COMPONENTS, WIDTH, HEIGHT))
trainPCA, evalPCA = projectEigens(toTrain_2d, toEvaluate_2d, pca)
classifier = setUpClassifier()
print(CLASSES)
classifier = fitClassifier(classifier, trainPCA, CLASSES)
predict(classifier, evalPCA, toEvalNames)
print(
"CLASSIFICATION is done successfuly. \nCheck file image_PCA_MLPerceptron.txt for the results."
)
def classify():
try:
f = open('img_pca_lda.model', 'rb')
except IOError:
print('Error: File with model parameters not found, please train the ',
+ 'classifier first.')
sys.exit()
# load the model parameters
model_parameters = pickle.load(f)
e_pca = model_parameters[0]
e_lda = model_parameters[1]
mean_x1 = model_parameters[2][0]
cov_x1 = model_parameters[2][1]
mean_x2 = model_parameters[3][0]
cov_x2 = model_parameters[3][1]
train_mean = model_parameters[4]
train_std = model_parameters[5]
# load the evaluation data
eval_data = list(png2fea(EVAL_DATA).items()) # evaluation data
# ...aaand classify the given data
count = 0
results = []
for filename, data in eval_data:
data = crop_image(data, 2, 2, 2, 2)
# standardise the data
data = data.flatten()
data -= train_mean
data /= train_std
data = (data.dot(e_pca)).dot(e_lda) # transform the test data
# compute the log-likelihood for the classified picture
ll_target = logpdf_gauss(data, mean_x1, np.atleast_2d(cov_x1))
ll_ntarget = logpdf_gauss(data, mean_x2, np.atleast_2d(cov_x2))
# compute the score of the picture
score = sum(ll_target) - sum(ll_ntarget)
# make the hard decision
if score >= THRESHOLD: decision = 1; count += 1 # target
else: decision = 0 # non-target
results.append(filename.split('/')[-1].split('.')[0]
+ ' ' + str(np.around(score, decimals=8))
+ ' ' + str(decision))
results.sort()
output = open('image_pca_lda_gaussian.txt', 'w')
for result in results: print(result, file=output)
if PRINT_STATS: print(f'Targets found: {count}')
output.close()
import numpy as np
from ikrlib import png2fea, wav16khz2mfcc
import re
data_folder_path = "../data/eval"
img_model_path = "cnn_image.h5"
voice_model_path = "nn_voice.h5"
data = []
labels = []
voice_model = load_model(voice_model_path, compile=True)
img_model = load_model(img_model_path, compile=True)
data = {}
img_data = png2fea(data_folder_path)
img_model.summary()
output_file = open('./predict_image_output.txt', 'w')
print("[INFO] evaluating image classifier...")
for k, v in img_data.items():
#prepare data for model
i_test_x = np.vstack(tuple(v))
i_test_x = i_test_x.reshape(1, 80, 80, 3)
i_test_x = np.r_[i_test_x]
i_test_x = i_test_x.astype('float32')
i_test_x /= 255
#prediction
predictions = img_model.predict_proba(i_test_x)
p = np.argmax(predictions)
from keras import layers
from keras import models
from keras import optimizers
from keras import utils
from keras.layers.advanced_activations import LeakyReLU
from ikrlib import png2fea
import numpy as np
import matplotlib.pyplot as plt
import datetime
import time
# Load data
train_t = np.vstack(tuple(png2fea('../data/target_train').values()))
print(train_t.shape)
train_t = train_t.reshape(train_t.shape[0] // 80, 80, 80, 3)
print(train_t.shape)
train_n = np.vstack(tuple(png2fea('../data/non_target_train').values()))
print(train_n.shape)
train_n = train_n.reshape(train_n.shape[0] // 80, 80, 80, 3)
print(train_t.shape)
val_t = np.vstack(tuple(png2fea('../data/target_dev').values()))
print(val_t.shape)
val_t = val_t.reshape(val_t.shape[0] // 80, 80, 80, 3)
print(val_t.shape)
val_n = np.vstack(tuple(png2fea('../data/non_target_dev').values()))
print(val_n.shape)
val_n = val_n.reshape(val_n.shape[0] // 80, 80, 80, 3)
test = {}
average = np.zeros((80, 80), dtype=np.float64).reshape(-1)
train_set_names = []
train_set_list = []
test_set_names = []
test_set_list = []
num = 185
img_counter = 0
for i in range(1, 32):
train[i] = png2fea("./train/" + str(i))
for key in train[i]:
tmp = train[i][key].reshape(-1)
train_set_list.append(tmp)
train_set_names.append(i)
average += tmp
img_counter += 1
average = average / float(img_counter)
#plt.imshow(average.reshape(80, 80), cmap="gray")
#plt.show()
test_counter = 0
for i in range(1, 2):