securetorobert

# Create the input vector for  images
inputs = Input((WIDTH, HEIGHT))

# The first layer is the preprocessing layer, which is bound to the input vector
x = Normalize()(inputs)

# Implement LeNet
x = tf.layers.Conv2D(filters=6, kernel_size=(5,5), strides=1, activation='tanh', input_shape=(HEIGHT, HEIGHT, NUM_CHANNELS))(x)
x = tf.layers.AveragePooling2D(pool_size=(2,2))(x)
x = tf.layers.Conv2D(filters=16, kernel_size=(5,5), strides=1, activation='tanh')(x)

securetorobert

class Normalize(layers.Layer):
    """ Custom Layer for Preprocessing Input """
    def __init__(self):
        """ Constructor """
        super(Normalize, self).__init__()
    
    def build(self, input_shape):
        """ Handler for Input Shape """
        self.kernel = None
    

securetorobert

optimizer = optimizers.SGD(learning_rate=0.01, momentum=0.9, decay=0.0005)

model.compile(optimizer=optimizer, loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(ds, epochs=1, steps_per_epoch=2)

securetorobert

model = models.Sequential([
    layers.Conv2D(filters=96, kernel_size=(11, 11), strides=4, activation='relu', input_shape=(HEIGHT, WIDTH, NUM_CHANNELS), bias_initializer=tf.initializers.zeros(), kernel_initializer=tf.initializers.RandomNormal(mean=0, stddev=0.01)),
    layers.BatchNormalization(),
    layers.MaxPooling2D(),
    layers.Conv2D(filters=256, kernel_size=(5, 5), activation='relu', bias_initializer=tf.initializers.ones(), kernel_initializer=tf.initializers.RandomNormal(mean=0, stddev=0.01)),
    layers.BatchNormalization(),
    layers.MaxPooling2D(),
    layers.Conv2D(filters=384, kernel_size=(3, 3), activation='relu', bias_initializer=tf.initializers.zeros(), kernel_initializer=tf.initializers.RandomNormal(mean=0, stddev=0.01)),
    layers.Conv2D(filters=384, kernel_size=(3, 3), activation='relu', bias_initializer=tf.initializers.ones(), kernel_initializer=tf.initializers.RandomNormal(mean=0, stddev=0.01)),

securetorobert

#standardSQL 
SELECT  
  weight_pounds, 
  state, 
  year, 
  gestation_weeks 
FROM  
  `bigquery-public-data.samples.natality` 
ORDER BY 
  weight_pounds 

securetorobert

predictors['rm_2'] = predictors['rm'].map(lambda x: x**2)
predictors['rm_3'] = predictors['rm'].map(lambda x: x**3)

securetorobert

predictors = train_df[['zn','rm', 'black', 'crim', 'indus', 'nox', 'rad', 'tax', 'ptratio']]
target = train_df['medv']

securetorobert

from sklearn.metrics import mean_squared_error

print('Score: {}'.format(lr.score(X_test, y_test)))
print('MSE: {}'.format(mean_squared_error(y_test, y_pred)))

securetorobert

y_pred = lr.predict(X_test)

_preds_df = pd.DataFrame(dict(observed=y_test, predicted=y_pred))
_preds_df.head()

securetorobert

from sklearn.linear_model import LinearRegression

lr = LinearRegression()
lr.fit(X_train, y_train)