import multiprocessing as mp
import time, logging, itertools
import cv2 as cv
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from distutils.version import StrictVersion
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image

from object_detection.utils import ops as utils_ops

from object_detection.utils import label_map_util

from object_detection.utils import visualization_utils as vis_util


def run_inference_for_single_image(sess, image, graph):
  with graph.as_default():
      # Get handles to input and output tensors
      ops = tf.get_default_graph().get_operations()
      all_tensor_names = {output.name for op in ops for output in op.outputs}
      tensor_dict = {}
      for key in [
          'num_detections', 'detection_boxes', 'detection_scores',
          'detection_classes', 'detection_masks'
      ]:
        tensor_name = key + ':0'
        if tensor_name in all_tensor_names:
          tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(
              tensor_name)
      if 'detection_masks' in tensor_dict:
        # The following processing is only for single image
        detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
        detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
        # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
        real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
        detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
        detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
        detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
            detection_masks, detection_boxes, image.shape[1], image.shape[2])
        detection_masks_reframed = tf.cast(
            tf.greater(detection_masks_reframed, 0.5), tf.uint8)
        # Follow the convention by adding back the batch dimension
        tensor_dict['detection_masks'] = tf.expand_dims(
            detection_masks_reframed, 0)
      image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')

      # Run inference
      output_dict = sess.run(tensor_dict,
                             feed_dict={image_tensor: image})

      # all outputs are float32 numpy arrays, so convert types as appropriate
      output_dict['num_detections'] = int(output_dict['num_detections'][0])
      output_dict['detection_classes'] = output_dict[
          'detection_classes'][0].astype(np.uint8)
      output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
      output_dict['detection_scores'] = output_dict['detection_scores'][0]
      if 'detection_masks' in output_dict:
        output_dict['detection_masks'] = output_dict['detection_masks'][0]
  return output_dict



# Holds a frame (numpy array) and creates current timestamp and autoincremental sequence number
class frame_container:
    counter = itertools.count()
    def __init__(self, frame):
        self.frame = frame
        self.timestamp = time.time()
        self.seq = next(self.counter)

# Plays the last frame generated by the object detection model
def video_player(q):
    while True:
        if not q.empty():
            frame = q.get()
            if debug == 1: print("[VP] Received frame #{}".format(frame.seq))
        else:
            continue
        cv.imshow('SSD Output', frame.frame)
        if cv.waitKey(1000 // fps) & 0xFF == ord('q'):
            break

# Puts frames into the model process queue, downsampling FPS from 30 to 5
def producer(q):
    cap = cv.VideoCapture('road.mp4')
    n_frame = 0
    while (cap.isOpened()):
        ret, frame = cap.read()
        if not ret:
            cap = cv.VideoCapture('road.mp4')
            continue
        dims = frame.shape[:2]
        max_side = np.max(dims)
        res = cv.resize(frame, None, fx=500 / max_side, fy=500 / max_side, interpolation=cv.INTER_CUBIC)
        if not q.full():
            if n_frame == 0:
                frame = frame_container(res)
                q.put(frame, False)
                # cv.imshow('Original Video', frame.frame)
                if cv.waitKey(1000 // fps) & 0xFF == ord('q'):
                    break
                if debug == 1: print("[P] Produced frame #{}".format(frame.seq))
        n_frame = (n_frame + 1) % 6
    cap.release()
    cv.destroyAllWindows()

# Waits for #batch_size frames and runs them through the object detection model, sending output to the video player process
def consumer(q, output_q):
    # What model to download.
    MODEL_NAME = 'ssd_mobilenet_v1_coco_2018_01_28'
    MODEL_FILE = MODEL_NAME + '.tar.gz'
    DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

    # Path to frozen detection graph. This is the actual model that is used for the object detection.
    PATH_TO_FROZEN_GRAPH = MODEL_NAME + '/frozen_inference_graph.pb'

    # List of the strings that is used to add correct label for each box.
    PATH_TO_LABELS = os.path.abspath('../data/mscoco_label_map.pbtxt')

    # Uncomment to download new model
    # opener = urllib.request.URLopener()
    # opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
    # tar_file = tarfile.open(MODEL_FILE)
    # for file in tar_file.getmembers():
    #     file_name = os.path.basename(file.name)
    #     if 'frozen_inference_graph.pb' in file_name:
    #         tar_file.extract(file, os.getcwd())

    detection_graph = tf.Graph()
    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
            serialized_graph = fid.read()
            od_graph_def.ParseFromString(serialized_graph)
            tf.import_graph_def(od_graph_def, name='')

    category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)

    model_output_imgs = []
    input_images = []
    inference_samples_num = 4
    beta = 1 - 1 / inference_samples_num
    inference_avg = -1
    inference_current = -1
    drift = 0

    with tf.Session(graph=detection_graph) as sess:
        while True:

            if not q.empty():
                if debug == 1: print("[C] Drift: {}".format(drift))
                frame = q.get()
                input_images.append(frame)

                # Drift is how much behind schedule the current frame is.
                # If more than one entire frame behind, skip this frame.
                if drift >= 1 / fps:
                    drift -= 1 / fps
                    input_images.pop(0)
                    if debug >= 1: print("[C] Skipping frame #{}".format(frame.seq))
                else:
                    drift += max(inference_current / batch_size - 1 / fps, 0)
            if len(input_images) >= batch_size:
                tick = time.time()
                if debug == 1: print("[C] Q, I, O, P size: ({}, {}, {}, {})".format(q.qsize(), len(input_images), len(model_output_imgs), output_q.qsize()))
                for i in range(batch_size):
                    minitick = time.time()
                    current_frame = input_images.pop(0)
                    image_np = current_frame.frame
                    # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
                    image_np_expanded = np.expand_dims(image_np, axis=0)
                    # Actual detection.
                    output_dict = run_inference_for_single_image(sess, image_np_expanded, detection_graph)
                    # Visualization of the results of a detection.
                    vis_util.visualize_boxes_and_labels_on_image_array(
                        image_np,
                        output_dict['detection_boxes'],
                        output_dict['detection_classes'],
                        output_dict['detection_scores'],
                        category_index,
                        instance_masks=output_dict.get('detection_masks'),
                        use_normalized_coordinates=True,
                        line_thickness=2)
                    current_frame.frame = image_np
                    minitock = time.time()
                    output_q.put(current_frame, False)

                    # Fake delay so that batch inference time is >2
                    # if minitock - minitick < 2 / batch_size:
                    #     time.sleep(2 / batch_size - (time.time() - minitick))
                tock = time.time()
                inference_current = (tock - tick)
                if inference_avg < 0:
                    inference_avg = inference_current
                inference_avg = beta * inference_avg + (1 - beta) * inference_current
                print("[C] Inference current batch: {}".format(inference_current))
                # print("[C] Inference average: {}".format(inference_avg))

    cv.destroyAllWindows()

# logger = mp.log_to_stderr(logging.DEBUG)

fps = 5
batch_size = 8
debug = 2
# 0: inference time
# 1: everything
# 2: skipped frames

consumer_in_q = mp.Queue(20)
consumer_out_q = mp.Queue(20)

#Producer process
p_proc = mp.Process(target=producer, args=(consumer_in_q,))
#Consumer process
c_proc = mp.Process(target=consumer, args=(consumer_in_q, consumer_out_q))
#Video player process
player = mp.Process(target=video_player, args=(consumer_out_q,))

p_proc.start()
c_proc.start()
player.start()