train image data with cnn

CNN_X_Y.py

import glob
from importlib.resources import path
from os import listdir
from os.path import isfile, join
import cv2
import os
import numpy as np
from random import shuffle
# from tqdm import tqdm
import pandas as pd


train_data=[]

path="/home/myn/Computer_Vision/Age detection/face_age"

for label in os.listdir(path):

    images = glob.glob(path+'/'+label+'/*.png')

    # df = pd.DataFrame(list(zip(images, label)),
    #            columns =['Image', 'Label'])

    for i in images:
        img = cv2.imread(i, cv2.IMREAD_GRAYSCALE)
        train_data.append([np.array(img), np.array(label)])

 
# print(train_data[1])
np.save('train_data.npy', train_data)



# Splitting the testing data and training data
train = train_data[:-6000]
test = train_data[-6000:]
IMG_SIZE = 200

'''Setting up the features and labels'''

# X-Features & Y-Labels
X = np.array([i[0] for i in train]).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
Y = [i[1] for i in train]
test_x = np.array([i[0] for i in test]).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
test_y = [i[1] for i in test]


LR = 1e-3
MODEL_NAME = 'dogsvscats-{}-{}.model'.format(LR, '6conv-basic')


import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
 
import tensorflow as tf
tf.reset_default_graph()
convnet = input_data(shape =[None, IMG_SIZE, IMG_SIZE , 1], name ='input')
 
convnet = conv_2d(convnet, 32, 5, activation ='relu')
convnet = max_pool_2d(convnet, 5)
 
convnet = conv_2d(convnet, 64, 5, activation ='relu')
convnet = max_pool_2d(convnet, 5)
 
convnet = conv_2d(convnet, 128, 5, activation ='relu')
convnet = max_pool_2d(convnet, 5)
 
convnet = conv_2d(convnet, 64, 5, activation ='relu')
convnet = max_pool_2d(convnet, 5)
 
convnet = conv_2d(convnet, 32, 5, activation ='relu')
convnet = max_pool_2d(convnet, 5)
 
convnet = fully_connected(convnet, 1024, activation ='relu')
convnet = dropout(convnet, 0.8)
 
convnet = fully_connected(convnet, 2, activation ='softmax')
convnet = regression(convnet, optimizer ='adam', learning_rate = LR,
      loss ='categorical_crossentropy', name ='targets')
 
model = tflearn.DNN(convnet, tensorboard_dir ='log')

 
# '''Fitting the data into our model'''
# epoch = 5 taken

model.fit({'input': X}, {'targets': Y}, n_epoch = 5,
    validation_set =({'input': test_x}, {'targets': test_y}),
    snapshot_step = 6000, show_metric = True, run_id = MODEL_NAME)

model.save(MODEL_NAME)