shepai

class model:
    def __init__(self,outcomes=10):
        self.model = Sequential()
        self.model.add(Conv2D(28, (3, 3), activation='relu', input_shape=(28, 28, 1)))
        self.model.add(MaxPooling2D((2, 2)))
        self.model.add(Conv2D(64, (3, 3), activation='relu'))
        self.model.add(MaxPooling2D((2, 2)))
        self.model.add(Conv2D(64, (3, 3), activation='relu'))
        self.model.add(Flatten())
        self.model.add(Dense(outcomes, activation='sigmoid')) #sigmoid is good for binary

shepai

"""
Normalize datasets
"""
#perform preprocessing scaling of the data
toTrain=train_X.reshape(len(train_X),28*28)
toTest=test_X.reshape(len(test_X),28*28)

scaler1 = preprocessing.StandardScaler().fit(toTrain)
X_standard_train = scaler1.transform(toTrain)
scaler2 = preprocessing.StandardScaler().fit(toTest)

shepai

m = train_X.shape[1]
n = train_X.shape[2]

def mandelbrot(height, width, x_from=0, x_to=0.1, y_from=0, y_to=0.1, max_iterations=100):
    x = np.linspace(x_from, x_to, width).reshape((1, width))
    y = np.linspace(y_from, y_to, height).reshape((height, 1))
    c = x + 1j * y
    return c
C=mandelbrot(1,28*28).reshape(28,28)

shepai

class model:
    def __init__(self,outcomes=10,numCells=28*28):
        self.model = Sequential()
        self.model.add(Dense(100, input_dim=numCells, activation='relu')) #4000 inputs compressed to 200
        #model.add(Dense(100, activation='relu')) #keep abstracting information
        #model.add(Dense(10, activation='relu'))
        self.model.add(Dense(outcomes, activation='sigmoid')) #sigmoid is good for binary
        self.model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

    def train(self,x,y,epochs=30,batch=32):