you can find source code of CNN (keras) but, you need to fix it for applying your dataset. next step, np.array -> make list of data and label customize your dataset (including dimension)-> np.expand_dims(x_train, -1) if you don't use multi channel data, make data shape " (x, x, 1) ' like 32,32,1 (ex, RGB data : 32,32,3) # 2022093021 import os import datetime import threading import time import matplotlib.pyplot as plt import numpy as np import math import tensorflow as tf from keras import datas...
#
64
#
choose
#
flatten
#
fully
#
normalize
#
one
#
output
#
randomly
