data_preprocess.py

labels = []
img_names = []
img_paths = []
gender = []
for file in os.listdir(dir):
    if file.endswith('.txt'):
        with open(os.path.join(dir, file), 'r') as t:
            content = t.readlines()
            gender.append(content[0].rsplit(' ')[1][0])
            img_name = content[2].rsplit(' ')[1][:-4] + '.png'
            img_paths.append(os.path.join(dir,img_name))
            img_names.append(img_name)
            labels.append((content[1].rsplit(' ')[1][0]))           
df = pd.DataFrame()
df['IMAGE PATH'] = img_paths
df['IMAGE NAME'] = img_names
df['LABEL'] = labels
df['GENDER'] = gender