#  Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
#  Licensed under the Apache License, Version 2.0 (the "License");
#  you may not use this file except in compliance with the License.
#  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
#  limitations under the License.
"""Convolutional Neural Network Estimator for MNIST, built with tf.layers."""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import tensorflow as tf

tf.logging.set_verbosity(tf.logging.INFO)

def serving_input_fn():
  inputs = {'x': tf.placeholder(tf.float32, [None, 28, 28], name="input_layer")}
  return tf.estimator.export.ServingInputReceiver(inputs, inputs)

def parse_args():
  import argparse, os
  parser = argparse.ArgumentParser()
  parser.add_argument('--train', type=str, default=os.environ['SM_CHANNEL_TRAIN'])
  parser.add_argument('--test', type=str, default=os.environ['SM_CHANNEL_TEST'])
  parser.add_argument('--model_dir', type=str)
  parser.add_argument('--sm-model-dir', type=str, default=os.environ['SM_MODEL_DIR'])
  parser.add_argument('--training-steps', type=int, default=20)
  args, _ = parser.parse_known_args()
  return args


def cnn_model_fn(features, labels, mode):
  """Model function for CNN."""
  # Input Layer
  # Reshape X to 4-D tensor: [batch_size, width, height, channels]
  # MNIST images are 28x28 pixels, and have one color channel
  input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

  # Convolutional Layer #1
  # Computes 32 features using a 5x5 filter with ReLU activation.
  # Padding is added to preserve width and height.
  # Input Tensor Shape: [batch_size, 28, 28, 1]
  # Output Tensor Shape: [batch_size, 28, 28, 32]
  conv1 = tf.layers.conv2d(
      inputs=input_layer,
      filters=32,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)

  # Pooling Layer #1
  # First max pooling layer with a 2x2 filter and stride of 2
  # Input Tensor Shape: [batch_size, 28, 28, 32]
  # Output Tensor Shape: [batch_size, 14, 14, 32]
  pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)

  # Convolutional Layer #2
  # Computes 64 features using a 5x5 filter.
  # Padding is added to preserve width and height.
  # Input Tensor Shape: [batch_size, 14, 14, 32]
  # Output Tensor Shape: [batch_size, 14, 14, 64]
  conv2 = tf.layers.conv2d(
      inputs=pool1,
      filters=64,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)

  # Pooling Layer #2
  # Second max pooling layer with a 2x2 filter and stride of 2
  # Input Tensor Shape: [batch_size, 14, 14, 64]
  # Output Tensor Shape: [batch_size, 7, 7, 64]
  pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)

  # Flatten tensor into a batch of vectors
  # Input Tensor Shape: [batch_size, 7, 7, 64]
  # Output Tensor Shape: [batch_size, 7 * 7 * 64]
  pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64])

  # Dense Layer
  # Densely connected layer with 1024 neurons
  # Input Tensor Shape: [batch_size, 7 * 7 * 64]
  # Output Tensor Shape: [batch_size, 1024]
  dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)

  # Add dropout operation; 0.6 probability that element will be kept
  dropout = tf.layers.dropout(
      inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)

  # Logits layer
  # Input Tensor Shape: [batch_size, 1024]
  # Output Tensor Shape: [batch_size, 10]
  logits = tf.layers.dense(inputs=dropout, units=10)

  predictions = {
      # Generate predictions (for PREDICT and EVAL mode)
      "classes": tf.argmax(input=logits, axis=1),
      # Add `softmax_tensor` to the graph. It is used for PREDICT and by the
      # `logging_hook`.
      "probabilities": tf.nn.softmax(logits, name="softmax_tensor")
  }
  if mode == tf.estimator.ModeKeys.PREDICT:
    return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)

  # Calculate Loss (for both TRAIN and EVAL modes)
  loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

  # Configure the Training Op (for TRAIN mode)
  if mode == tf.estimator.ModeKeys.TRAIN:
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
    train_op = optimizer.minimize(
        loss=loss,
        global_step=tf.train.get_global_step())
    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)

  # Add evaluation metrics (for EVAL mode)
  eval_metric_ops = {
      "accuracy": tf.metrics.accuracy(
          labels=labels, predictions=predictions["classes"])}
  return tf.estimator.EstimatorSpec(
      mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)

def main(unused_argv):
  args = parse_args()
  train_dir = args.train
  test_dir = args.test
  model_dir = args.model_dir
  sm_model_dir = args.sm_model_dir
  training_steps = args.training_steps
    
#def main(unused_argv):
  # Load training and eval data
  #mnist = tf.contrib.learn.datasets.load_dataset("mnist")
  #train_data = mnist.train.images  # Returns np.array
  #train_labels = np.asarray(mnist.train.labels, dtype=np.int32)
  #eval_data = mnist.test.images  # Returns np.array
  #eval_labels = np.asarray(mnist.test.labels, dtype=np.int32)

  import os
  train_data = np.load(os.path.join(train_dir, 'image.npy')).astype(np.float32) * 1./255
  train_labels = np.load(os.path.join(train_dir, 'label.npy')).astype(np.int32)
  eval_data = np.load(os.path.join(test_dir, 'image.npy')).astype(np.float32) * 1./255
  eval_labels = np.load(os.path.join(test_dir, 'label.npy')).astype(np.int32)
  # Create the Estimator

  mnist_classifier = tf.estimator.Estimator(
      model_fn=cnn_model_fn, model_dir=model_dir)
    
  #mnist_classifier = tf.estimator.Estimator(
  #    model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")

  # Set up logging for predictions
  # Log the values in the "Softmax" tensor with label "probabilities"
  tensors_to_log = {"probabilities": "softmax_tensor"}
  logging_hook = tf.train.LoggingTensorHook(
      tensors=tensors_to_log, every_n_iter=50)

  # Train the model
  train_input_fn = tf.compat.v1.estimator.inputs.numpy_input_fn(
      x={"x": train_data},
      y=train_labels,
      batch_size=100,
      num_epochs=None,
      shuffle=True)
  mnist_classifier.train(
      input_fn=train_input_fn,
      steps=training_steps, #default:20000
      hooks=[logging_hook])

  # Evaluate the model and print results
  #eval_input_fn = tf.compat.v1.estimator.inputs.numpy_input_fn(
  #    x={"x": eval_data}, y=eval_labels, num_epochs=1, shuffle=False)
  #eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn)
  #print(eval_results)

  # Evaluate the model and print results
  eval_input_fn = tf.compat.v1.estimator.inputs.numpy_input_fn(
      x={"x": eval_data}, y=eval_labels, num_epochs=1, shuffle=False)
  eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn)
  print(eval_results)

  mnist_classifier.export_savedmodel(sm_model_dir, serving_input_fn)
    
if __name__ == "__main__":
  tf.app.run()