Keras/Jupyter Stuff

keras_to_tf.keras.py

import tensorflow as tf
import tf.keras as keras

# Configure a model for categorical classification.
model.compile(optimizer=tf.train.RMSPropOptimizer(0.01),
              loss=keras.losses.categorical_crossentropy,
              metrics=[keras.metrics.categorical_accuracy])

estimator = keras.estimator.model_to_estimator(model)

# tf dataset
dataset = tf.data.Dataset.from_tensor_slices((data, labels))
dataset = dataset.batch(32).repeat()

val_dataset = tf.data.Dataset.from_tensor_slices((val_data, val_labels))
val_dataset = val_dataset.batch(32).repeat()

model.fit(dataset, epochs=10, steps_per_epoch=30,
          validation_data=val_dataset,
          validation_steps=3)

def input_fn():
  x = np.random.random((1024, 10))
  y = np.random.randint(2, size=(1024, 1))
  x = tf.cast(x, tf.float32)
  dataset = tf.data.Dataset.from_tensor_slices((x, y))
  dataset = dataset.repeat(10)
  dataset = dataset.batch(32)
  return dataset

strategy = tf.contrib.distribute.MirroredStrategy()
config = tf.estimator.RunConfig(train_distribute=strategy)

keras_estimator = keras.estimator.model_to_estimator(
  keras_model=model,
  config=config,
  model_dir='/tmp/model_dir')

keras_estimator.train(input_fn=input_fn, steps=10)

snippets.py

%matplotlib inline
%config InlineBackend.figure_format = 'retina'

# GPU selection
import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "0"

# loading from pickle
with open("datasets/sst_train_texts.pickle", 'rb') as handle:
    sst_train = pickle.load(handle)

# loading from text file
lines = [line.rstrip('\n') for line in open('filename')]

# multi-gpu model
import tensorflow as tf
from keras.utils.training_utils import multi_gpu_model

with tf.device("/cpu:0"):
		# initialize the model
		model = XXX
	
# make the model parallel
parallel_model = multi_gpu_model(model, gpus=2)