def _evaluate_distributed(self, dataset):
predictor = TFPredictor(K.get_session(), self.metrics_tensors,
self.model.inputs + self.model.targets,
dataset)
result = predictor.predict()
metrics_sum = result.map(lambda x: x + [np.array(1.0)]).reduce(
lambda a, b: elem_sum(a, b))
length = len(metrics_sum) - 1
for i in range(length):
metrics_sum[i] /= metrics_sum[length]
return metrics_sum[:length]
def main():
sc = init_nncontext()
# get data, pre-process and create TFDataset
(images_data, labels_data) = mnist.read_data_sets("/tmp/mnist", "test")
image_rdd = sc.parallelize(images_data)
labels_rdd = sc.parallelize(labels_data)
rdd = image_rdd.zip(labels_rdd) \
.map(lambda rec_tuple: [normalizer(rec_tuple[0], mnist.TRAIN_MEAN, mnist.TRAIN_STD),
np.array(rec_tuple[1])])
dataset = TFDataset.from_rdd(rdd,
names=["features", "labels"],
shapes=[[28, 28, 1], [1]],
types=[tf.float32, tf.int32],
batch_per_thread=20)
# construct the model from TFDataset
images, labels = dataset.tensors
labels = tf.squeeze(labels)
with slim.arg_scope(lenet.lenet_arg_scope()):
logits, end_points = lenet.lenet(images,
num_classes=10,
is_training=False)
predictions = tf.to_int32(tf.argmax(logits, axis=1))
correct = tf.expand_dims(tf.to_int32(tf.equal(predictions, labels)),
axis=1)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, "/tmp/lenet/")
predictor = TFPredictor(sess, [correct])
accuracy = predictor.predict().mean()
print("predict accuracy is %s" % accuracy)
def main(data_num):
data = Input(shape=[28, 28, 1])
x = Flatten()(data)
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=data, outputs=predictions)
model.load_weights("/tmp/mnist_keras.h5")
if DISTRIBUTED:
# using RDD api to do distributed evaluation
sc = init_nncontext()
# get data, pre-process and create TFDataset
(images_data, labels_data) = mnist.read_data_sets("/tmp/mnist", "test")
image_rdd = sc.parallelize(images_data[:data_num])
labels_rdd = sc.parallelize(labels_data[:data_num])
rdd = image_rdd.zip(labels_rdd) \
.map(lambda rec_tuple: [normalizer(rec_tuple[0], mnist.TRAIN_MEAN, mnist.TRAIN_STD)])
dataset = TFDataset.from_rdd(rdd,
names=["features"],
shapes=[[28, 28, 1]],
types=[tf.float32],
batch_per_thread=20)
predictor = TFPredictor.from_keras(model, dataset)
accuracy = predictor.predict().zip(labels_rdd).map(
lambda x: np.argmax(x[0]) == x[1]).mean()
print("predict accuracy is %s" % accuracy)
else:
# using keras api for local evaluation
model.compile(optimizer='rmsprop',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
(images_data, labels_data) = mnist.read_data_sets("/tmp/mnist", "test")
images_data = normalizer(images_data, mnist.TRAIN_MEAN,
mnist.TRAIN_STD)
result = model.evaluate(images_data, labels_data)
print(model.metrics_names)
print(result)
def _predict_distributed(self, x):
predictor = TFPredictor.from_keras(self.model, x)
return predictor.predict()
