# Copyright Amazon.com, Inc. or its affiliates. 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. A copy of
# the License is located at
#
#     http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file 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.
from __future__ import absolute_import, division, print_function

import argparse
import json
import numpy as np
import os
import tensorflow as tf

tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.DEBUG)


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.compat.v1.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.compat.v1.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.compat.v1.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.compat.v1.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.compat.v1.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)

    # Add dropout operation; 0.6 probability that element will be kept
    dropout = tf.compat.v1.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.compat.v1.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.compat.v1.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

    # Configure the Training Op (for TRAIN mode)
    if mode == tf.estimator.ModeKeys.TRAIN:
        optimizer = tf.compat.v1.train.GradientDescentOptimizer(learning_rate=0.001)
        train_op = optimizer.minimize(loss=loss, global_step=tf.compat.v1.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.compat.v1.metrics.accuracy(labels=labels, predictions=predictions["classes"])
    }
    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)


def _load_training_data(base_dir):
    x_train = np.load(os.path.join(base_dir, "train_data.npy"))
    y_train = np.load(os.path.join(base_dir, "train_labels.npy"))
    return x_train, y_train


def _load_testing_data(base_dir):
    x_test = np.load(os.path.join(base_dir, "eval_data.npy"))
    y_test = np.load(os.path.join(base_dir, "eval_labels.npy"))
    return x_test, y_test


def _parse_args():

    parser = argparse.ArgumentParser()

    # hyperparameters sent by the client are passed as command-line arguments to the script.
    parser.add_argument("--epochs", type=int, default=1)
    # Data, model, and output directories
    parser.add_argument("--output-data-dir", type=str, default=os.environ.get("SM_OUTPUT_DATA_DIR"))
    parser.add_argument("--model_dir", type=str)
    parser.add_argument("--train", type=str, default=os.environ.get("SM_CHANNEL_TRAINING"))
    parser.add_argument("--hosts", type=list, default=json.loads(os.environ.get("SM_HOSTS")))
    parser.add_argument("--current-host", type=str, default=os.environ.get("SM_CURRENT_HOST"))

    return parser.parse_known_args()


def serving_input_fn():
    inputs = {"x": tf.compat.v1.placeholder(tf.float32, [None, 784])}
    return tf.estimator.export.ServingInputReceiver(inputs, inputs)


def main(args):
    if args.model_dir.startswith("s3://"):
        os.environ["S3_REGION"] = "us-west-2"
        os.environ["TF_CPP_MIN_LOG_LEVEL"] = "1"
        os.environ["S3_USE_HTTPS"] = "1"

    train_data, train_labels = _load_training_data(args.train)
    eval_data, eval_labels = _load_testing_data(args.train)

    # Create the Estimator
    mnist_classifier = tf.estimator.Estimator(model_fn=cnn_model_fn, model_dir=args.model_dir)

    # Set up logging for predictions
    # Log the values in the "Softmax" tensor with label "probabilities"
    tensors_to_log = {"probabilities": "softmax_tensor"}
    logging_hook = tf.estimator.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=50, num_epochs=None, shuffle=False
    )

    # 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
    )

    train_spec = tf.estimator.TrainSpec(train_input_fn, max_steps=1000)
    eval_spec = tf.estimator.EvalSpec(eval_input_fn)
    tf.estimator.train_and_evaluate(mnist_classifier, train_spec, eval_spec)

    if args.current_host == args.hosts[0]:
        mnist_classifier.export_saved_model("/opt/ml/model", serving_input_fn)


if __name__ == "__main__":
    known, unknown = _parse_args()
    main(known)