hadifar

iris = datasets.load_iris()
X = iris.data[:, :2]
Y = iris.target

clf = MLPClassifier(solver='lbfgs', hidden_layer_sizes=(10,10))

# Create an instance of Logistic Regression Classifier and fit the data.
clf.fit(X, Y)

# Prediction phase

hadifar

NUM_GPUS = 4
strategy = tf.contrib.distribute.MirroredStrategy(num_gpus=NUM_GPUS)
config = tf.estimator.RunConfig(train_distribute=strategy)
estimator = tf.estimator.Estimator(model, config=config)

hadifar

# Instantiate a Keras inception v3 model.
keras_inception_v3 = tf.keras.applications.inception_v3.InceptionV3(weights=None)

keras_inception_v3.compile(optimizer=tf.keras.optimizers.SGD(lr=0.0001, momentum=0.9),
                          loss='categorical_crossentropy',
                          metric='accuracy')
                          
est_inception_v3 = tf.keras.estimator.model_to_estimator(keras_model=keras_inception_v3)

train_input_fn = tf.estimator.inputs.numpy_input_fn(

hadifar

model_estimator = tf.estimator.Estimator(model_fn=model_fn, model_dir='./tmp/')
model_estimator.train(train_input_fn, max_steps=5000)
result = model_estimator.evaluate(test_input_fn)
print(result)

hadifar

def neural_net_model(inputs, mode):
    with tf.variable_scope('ConvModel'):
        inputs = inputs / 255
        input_layer = tf.reshape(inputs, [-1, 28, 28, 1])
        conv1 = tf.layers.conv2d(
            inputs=input_layer,
            filters=20,
            kernel_size=[5, 5],
            padding='valid',
            activation=tf.nn.relu)

hadifar

def model_fn(features, labels, mode):
    logits = neural_net_model(features, mode)
    class_prediction = tf.argmax(logits, axis=-1)
    preds = class_prediction

    loss = None
    train_op = None
    eval_metric_ops = {}

    if mode in (tf.estimator.ModeKeys.EVAL, tf.estimator.ModeKeys.TRAIN):

hadifar

def model_fn(features, labels, mode, params, config)

hadifar

# Feature columns describe how to use the input.
my_feature_columns = []
for key in iris_data.train_x.keys():
    my_feature_columns.append(tf.feature_column.numeric_column(key=key))

# Build 2 hidden layer DNN with 10, 10 units respectively.
classifier = tf.estimator.DNNClassifier(
    feature_columns=my_feature_columns,
    # Two hidden layers of 10 nodes each.
    hidden_units=[10, 10],

hadifar

# Build 2 hidden layer DNN with 10, 10 units respectively.
classifier = tf.estimator.DNNClassifier(
    feature_columns=my_feature_columns,
    # Two hidden layers of 10 nodes each.
    hidden_units=[10, 10],
    # The model must choose between 3 classes.
    n_classes=3,
    # The directory which model to be saved
    model_dir='./tmp'
)

hadifar

def input_fn():
   ...  # manipulate dataset, extracting the feature dict and the label
   return feature_dict, label