I am extracting features from face images and then comparing features with other image using different similarity metrics. Previously, the list of images name is small and it works fine. The whole list which represented each image i put those list in json file and used in python file. When i increase the images, the PyCharm kill my process.
import pandas as pd
import numpy as np
import itertools
from sklearn import metrics
from sklearn.metrics import confusion_matrix, accuracy_score, roc_curve, auc
import matplotlib.pyplot as plt
import json
from tqdm import tqdm
from sklearn.utils.multiclass import type_of_target
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
tf.compat.v1.disable_eager_execution()
with open('/home/khawar/deepface/tests/ageDB.json') as f:
data = json.load(f)
idendities = data
# --------------------------
# Data set
# Ref: https://github.com/serengil/deepface/tree/master/tests/dataset
# --------------------------
# Positives
positives = []
for key, values in idendities.items():
# print(key)
for i in range(0, len(values) - 1):
for j in range(i + 1, len(values)):
# print(values[i], " and ", values[j])
positive = []
positive.append(values[i])
positive.append(values[j])
positives.append(positive)
positives = pd.DataFrame(positives, columns=["file_x", "file_y"])
positives["decision"] = "Yes"
print(positives.shape)
# --------------------------
# Negatives
samples_list = list(idendities.values())
negatives = []
for i in range(0, len(idendities) - 1):
for j in range(i + 1, len(idendities)):
# print(samples_list[i], " vs ",samples_list[j])
cross_product = itertools.product(samples_list[i], samples_list[j])
cross_product = list(cross_product)
# print(cross_product)
for cross_sample in cross_product:
# print(cross_sample[0], " vs ", cross_sample[1])
negative = []
negative.append(cross_sample[0])
negative.append(cross_sample[1])
negatives.append(negative)
negatives = pd.DataFrame(negatives, columns=["file_x", "file_y"])
negatives["decision"] = "No"
negatives = negatives.sample(positives.shape[0])
print(negatives.shape)
# --------------------------
# Merge positive and negative ones
df = pd.concat([positives, negatives]).reset_index(drop=True)
print(df.decision.value_counts())
df.file_x = "deepface/tests/dataset/" + df.file_x
df.file_y = "deepface/tests/dataset/" + df.file_y
# --------------------------
# DeepFace
from deepface import DeepFace
from deepface.basemodels import VGGFace, OpenFace, Facenet, FbDeepFace
pretrained_models = {}
pretrained_models["VGG-Face"] = VGGFace.loadModel()
print("VGG-Face loaded")
pretrained_models["Facenet"] = Facenet.loadModel()
print("Facenet loaded")
pretrained_models["OpenFace"] = OpenFace.loadModel()
print("OpenFace loaded")
pretrained_models["DeepFace"] = FbDeepFace.loadModel()
print("FbDeepFace loaded")
instances = df[["file_x", "file_y"]].values.tolist()
models = ['VGG-Face']
metrics = ['cosine']
if True:
for model in models:
for metric in metrics:
resp_obj = DeepFace.verify(instances
, model_name=model
, model=pretrained_models[model]
, distance_metric=metric)
distances = []
for i in range(0, len(instances)):
distance = round(resp_obj["pair_%s" % (i + 1)]["distance"], 4)
distances.append(distance)
df['%s_%s' % (model, metric)] = distances
df.to_csv("face-recognition-pivot.csv", index=False)
else:
df = pd.read_csv("face-recognition-pivot.csv")
df_raw = df.copy()
# --------------------------
# Distribution
fig = plt.figure(figsize=(15, 15))
figure_idx = 1
for model in models:
for metric in metrics:
feature = '%s_%s' % (model, metric)
ax1 = fig.add_subplot(4, 2, figure_idx)
df[df.decision == "Yes"][feature].plot(kind='kde', title=feature, label='Yes', legend=True)
df[df.decision == "No"][feature].plot(kind='kde', title=feature, label='No', legend=True)
figure_idx = figure_idx + 1
# plt.show()
# --------------------------
# Pre-processing for modelling
columns = []
for model in models:
for metric in metrics:
feature = '%s_%s' % (model, metric)
columns.append(feature)
columns.append("decision")
df = df[columns]
df.loc[df[df.decision == 'Yes'].index, 'decision'] = 1
df.loc[df[df.decision == 'No'].index, 'decision'] = 0
print(df.head())
# --------------------------
# Train test split
from sklearn.model_selection import train_test_split
df_train, df_test = train_test_split(df, test_size=0.30, random_state=17)
target_name = "decision"
y_train = df_train[target_name].values
x_train = df_train.drop(columns=[target_name]).values
y_test = df_test[target_name].values
x_test = df_test.drop(columns=[target_name]).values
# --------------------------
# LightGBM
import lightgbm as lgb
features = df.drop(columns=[target_name]).columns.tolist()
lgb_train = lgb.Dataset(x_train, y_train, feature_name=features)
lgb_test = lgb.Dataset(x_test, y_test, feature_name=features)
params = {
'task': 'train'
, 'boosting_type': 'gbdt'
, 'objective': 'multiclass'
, 'num_class': 2
, 'metric': 'multi_logloss'
}
gbm = lgb.train(params, lgb_train, num_boost_round=250, early_stopping_rounds=15, valid_sets=lgb_test)
gbm.save_model("face-recognition-ensemble-model.txt")
# --------------------------
# Evaluation
predictions = gbm.predict(x_test)
predictions_classes = []
for i in predictions:
prediction_class = np.argmax(i)
predictions_classes.append(prediction_class)
cm = confusion_matrix(list(y_test), predictions_classes)
tn, fp, fn, tp = cm.ravel()
recall = tp / (tp + fn)
precision = tp / (tp + fp)
accuracy = (tp + tn) / (tn + fp + fn + tp)
f1 = 2 * (precision * recall) / (precision + recall)
print("Precision: ", 100 * precision, "%")
print("Recall: ", 100 * recall, "%")
print("F1 score ", 100 * f1, "%")
print("Accuracy: ", 100 * accuracy, "%")
# --------------------------
# Interpretability
ax = lgb.plot_importance(gbm, max_num_features=20)
# plt.show()
import os
os.environ["PATH"] += os.pathsep + 'C:/Program Files (x86)/Graphviz2.38/bin'
plt.rcParams["figure.figsize"] = [20, 20]
for i in range(0, gbm.num_trees()):
ax = lgb.plot_tree(gbm, tree_index=i)
# plt.show()
if i == 2:
break
# --------------------------
# ROC Curve
from sklearn.metrics import confusion_matrix, accuracy_score, roc_auc_score, roc_curve
y_pred_proba = predictions[::, 1]
y_test = y_test.astype(int)
fpr, tpr, _ = roc_curve(y_test, y_pred_proba)
auc = roc_auc_score(y_test, y_pred_proba)
plt.figure(figsize=(4, 4))
lw = 2
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
fig.savefig('/home/khawar/deepface/tests/VGG-FACE_Cosine_ROC.png', dpi=fig.dpi)
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('VGG Face')
plt.plot(fpr, tpr, label="ROC=" + str(auc))
fig.savefig('/home/khawar/deepface/tests/VGG-FACE_Cosine_ROC_T_F.png', dpi=fig.dpi)
#plt.legend(loc=4)
#fig.savefig('/home/khawar/deepface/tests/VGG-FACE_Cosine.png', dpi=fig.dpi)
plt.show()
# --------------------------
Traceback
/home/khawar/anaconda3/envs/deepface/bin/python /home/khawar/deepface/tests/Ensemble-Face-Recognition.py
(236167, 3)
Process finished with exit code 137 (interrupted by signal 9: SIGKILL)