"""YOLO_v2 Model Defined in Keras."""
import sys

import numpy as np
import tensorflow as tf
from keras import backend as K
from keras.layers import Lambda, Reshape, merge
from keras.models import Model

from ..utils import compose
from .keras_darknet19 import (DarknetConv2D, DarknetConv2D_BN_Leaky,
                              darknet_body)

sys.path.append('..')

voc_anchors = np.array(
    [[1.08, 1.19], [3.42, 4.41], [6.63, 11.38], [9.42, 5.11], [16.62, 10.52]])

voc_classes = [
    "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat",
    "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person",
    "pottedplant", "sheep", "sofa", "train", "tvmonitor"
]


def space_to_depth_x2(x):
    """Thin wrapper for Tensorflow space_to_depth with block_size=2."""
    # Import currently required to make Lambda work.
    # See: https://github.com/fchollet/keras/issues/5088#issuecomment-273851273
    import tensorflow as tf
    return tf.space_to_depth(x, block_size=2)


def space_to_depth_x2_output_shape(input_shape):
    """Determine space_to_depth output shape for block_size=2.

    Note: For Lambda with TensorFlow backend, output shape may not be needed.
    """
    return (input_shape[0], input_shape[1] // 2, input_shape[2] // 2, 4 *
            input_shape[3]) if input_shape[1] else (input_shape[0], None, None,
                                                    4 * input_shape[3])


def yolo_body(inputs, num_anchors, num_classes):
    """Create YOLO_V2 model CNN body in Keras."""
    darknet = Model(inputs, darknet_body()(inputs))
    conv13 = darknet.get_layer('batchnormalization_13').output
    conv20 = compose(
        DarknetConv2D_BN_Leaky(1024, 3, 3),
        DarknetConv2D_BN_Leaky(1024, 3, 3))(darknet.output)

    # TODO: Allow Keras Lambda to use func arguments for output_shape?
    conv13_reshaped = Lambda(
        space_to_depth_x2,
        output_shape=space_to_depth_x2_output_shape,
        name='space_to_depth')(conv13)

    # Concat conv13 with conv20.
    x = merge([conv13_reshaped, conv20], mode='concat')
    x = DarknetConv2D_BN_Leaky(1024, 3, 3)(x)
    x = DarknetConv2D(num_anchors * (num_classes + 5), 1, 1)(x)
    return Model(inputs, x)


def yolo_head(feats, anchors, num_classes):
    """Convert final layer features to bounding box parameters.

    Parameters
    ----------
    feats : tensor
        Final convolutional layer features.
    anchors : array-like
        Anchor box widths and heights.
    num_classes : int
        Number of target classes.

    Returns
    -------
    box_xy : tensor
        x, y box predictions adjusted by spatial location in conv layer.
    box_wh : tensor
        w, h box predictions adjusted by anchors and conv spatial resolution.
    box_conf : tensor
        Probability estimate for whether each box contains any object.
    box_class_pred : tensor
        Probability distribution estimate for each box over class labels.
    """
    num_anchors = len(anchors)
    # Reshape to batch, height, width, num_anchors, box_params.
    anchors_tensor = K.reshape(K.variable(anchors), [1, 1, 1, num_anchors, 2])

    # Static implementation for fixed models.
    # TODO: Remove or add option for static implementation.
    # _, conv_height, conv_width, _ = K.int_shape(feats)
    # conv_dims = K.variable([conv_width, conv_height])

    # Dynamic implementation of conv dims for fully convolutional model.
    conv_dims = K.shape(feats)[1:3]  # assuming channels last
    # In YOLO the height index is the inner most iteration.
    conv_height_index = K.arange(0, stop=conv_dims[0])
    conv_width_index = K.arange(0, stop=conv_dims[1])
    conv_height_index = K.tile(conv_height_index, [conv_dims[0]])

    # TODO: Repeat_elements and tf.split doesn't support dynamic splits.
    # conv_width_index = K.repeat_elements(conv_width_index, conv_dims[1], axis=0)
    conv_width_index = K.tile(
        K.expand_dims(conv_width_index, 0), [conv_dims[1], 1])
    conv_width_index = K.flatten(K.transpose(conv_width_index))
    conv_index = K.transpose(K.stack([conv_height_index, conv_width_index]))
    conv_index = K.reshape(conv_index, [conv_dims[0], conv_dims[1], 2])
    conv_index = K.reshape(conv_index, [1, conv_dims[0], conv_dims[1], 1, 2])
    conv_index = K.cast(conv_index, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, conv_dims[0], conv_dims[1], num_anchors, num_classes + 5])
    conv_dims = K.cast(K.reshape(conv_dims, [1, 1, 1, 1, 2]), K.dtype(feats))

    # Static generation of conv_index:
    # conv_index = np.array([_ for _ in np.ndindex(conv_width, conv_height)])
    # conv_index = conv_index[:, [1, 0]]  # swap columns for YOLO ordering.
    # conv_index = K.variable(
    #     conv_index.reshape(1, conv_height, conv_width, 1, 2))
    # feats = Reshape(
    #     (conv_dims[0], conv_dims[1], num_anchors, num_classes + 5))(feats)

    box_xy = K.sigmoid(feats[..., :2])
    box_wh = K.exp(feats[..., 2:4])
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.softmax(feats[..., 5:])

    # Adjust preditions to each spatial grid point and anchor size.
    # Note: YOLO iterates over height index before width index.
    box_xy = (box_xy + conv_index) / conv_dims
    box_wh = box_wh * anchors_tensor / conv_dims

    return box_xy, box_wh, box_confidence, box_class_probs


def yolo_boxes_to_corners(box_xy, box_wh):
    """Convert YOLO box predictions to bounding box corners."""
    box_mins = box_xy - (box_wh / 2.)
    box_maxes = box_xy + (box_wh / 2.)

    return K.concatenate([
        box_mins[..., 1:2],  # y_min
        box_mins[..., 0:1],  # x_min
        box_maxes[..., 1:2],  # y_max
        box_maxes[..., 0:1]  # x_max
    ])


def yolo(inputs, anchors, num_classes):
    """Generate a complete YOLO_v2 localization model."""
    num_anchors = len(anchors)
    body = yolo_body(inputs, num_anchors, num_classes)
    outputs = yolo_head(body.output, anchors, num_classes)
    return outputs


def yolo_filter_boxes(boxes, box_confidence, box_class_probs, threshold=.6):
    """Filter YOLO boxes based on object and class confidence."""
    box_scores = box_confidence * box_class_probs
    box_classes = K.argmax(box_scores, axis=-1)
    box_class_scores = K.max(box_scores, axis=-1)
    prediction_mask = box_class_scores >= threshold

    # TODO: Expose tf.boolean_mask to Keras backend?
    boxes = tf.boolean_mask(boxes, prediction_mask)
    scores = tf.boolean_mask(box_class_scores, prediction_mask)
    classes = tf.boolean_mask(box_classes, prediction_mask)
    return boxes, scores, classes


def yolo_eval(yolo_outputs,
              image_shape,
              max_boxes=10,
              score_threshold=.6,
              iou_threshold=.5):
    """Evaluate YOLO model on given input batch and return filtered boxes."""
    box_xy, box_wh, box_confidence, box_class_probs = yolo_outputs
    boxes = yolo_boxes_to_corners(box_xy, box_wh)
    boxes, scores, classes = yolo_filter_boxes(
        boxes, box_confidence, box_class_probs, threshold=score_threshold)

    # Scale boxes back to original image shape.
    height = image_shape[0]
    width = image_shape[1]
    image_dims = K.stack([height, width, height, width])
    image_dims = K.reshape(image_dims, [1, 4])
    boxes = boxes * image_dims

    # TODO: Something must be done about this ugly hack!
    max_boxes_tensor = K.variable(max_boxes, dtype='int32')
    K.get_session().run(tf.variables_initializer([max_boxes_tensor]))
    nms_index = tf.image.non_max_suppression(
        boxes, scores, max_boxes_tensor, iou_threshold=iou_threshold)
    boxes = K.gather(boxes, nms_index)
    scores = K.gather(scores, nms_index)
    classes = K.gather(classes, nms_index)
    return boxes, scores, classes