import os 
import sys
import random
import math
import numpy as np
import cv2
import matplotlib.pyplot as plt
from tqdm import tqdm
import pandas as pd 
import glob
from sklearn.model_selection import KFold
from PIL import Image
import os.path
import glob
import traceback
import skimage

from skimage import data, color
from skimage.transform import rescale, resize, downscale_local_mean

from mrcnn.config import Config
from mrcnn import utils
import mrcnn.model as modellib
from mrcnn import visualize
from mrcnn.model import log

import os
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np

import tensorflow as tf

IMG_SIZE = 256

masks = [filename for filename in glob.iglob('../input/mask/' + '**/*.png', recursive=True)]

train_raw = [filename for filename in glob.iglob('../input/train/' + '**/*.jpg', recursive=True)]

len(train_raw)

mask_class = pd.read_csv('../tiny_input/class/classes-segmentation.txt', header=None)

mask_class = mask_class.reset_index()
mask_class['index'] = mask_class['index'] + 1

mask_class.columns = ['index','value']

mask_class.shape

mask_class.head(5)

mask_map = pd.DataFrame( [ i.rsplit('_',1)  for i in masks ] )
mask_map.columns = ['left','right']
mask_map['left1'] = mask_map['left'].apply(lambda x : x.split('_', 1)[0])
mask_map['left2'] = mask_map['left'].apply(lambda x : x.split('_', 1)[1])
mask_map['name'] = mask_map['left'].apply(lambda x: x.rsplit('\\', 1)[1])
mask_map['name_origin'] = mask_map['name'].apply(lambda x : x.split('_', 1)[0])

mask_map = mask_map[['name_origin', 'left2']]
mask_map.columns = ['train', 'object']
mask_map['origin'] = masks

mask_map.head(5)

mask_map_identifier = mask_map.set_index('train')

mask_map_identifier.head(5)

def check_if_mask_exists(filename):
    f = filename.rsplit('.jpg')[0][-16:]
    return f in mask_map_identifier.index

train = []
for file in train_raw:
    if check_if_mask_exists(file):
        train.append(file)

len(train)

def get_objects_from_train_image(train_image_name):
    return mask_map[mask_map['train']==train_image_name]

get_objects_from_train_image('50002559e6b827ed')

class_list = pd.read_csv('../tiny_input/class/classes-segmentation.txt', header=None)
class_list = class_list.reset_index()
class_list['index'] = class_list['index'] + 1
class_list.columns = ['image_index', 'object']
class_list['object'] = class_list['object'].apply(lambda x : x.replace('/',''))
print(class_list.head(10))

train_meta = pd.read_csv('image_meta.csv')

train_meta['image_name'] = train_meta['filepath'].apply(lambda x: x.rsplit('\\')[2].split('.jpg')[0])
train_meta.head(2)
train_meta = train_meta.set_index('filepath')

# 현재 mask가 있는것만 학습한다.
def get_wh_from_filepath(filepath):
    row = train_meta.loc[filepath]
    return row.width, row.height
#     return row.iloc[0]['width'], row.iloc[0]['height']

get_wh_from_filepath('../input/train\\train_1\\100009cf62726c53.jpg')

class_list[class_list['object'] == 'm02p0tk3']

file_name = '10086973aa2c6d00.jpg'

print(file_name)

w = 576
h = 1024

# 관련된 이미지 다 긁어옴. train / object / mask filepath
df_objects = get_objects_from_train_image(file_name.rsplit('.jpg')[0][-16:])
df_objects

class DetectorDataset(utils.Dataset):
    
    # 미리 파일을 로딩한다. 하나의 이미지에 복수의 segmentation가능
    def load_dataset(self, start, end):
        
        # class에 대한 정보를 넣는다.
        for (i, c) in enumerate(class_list['object'], 1):
            self.add_class('openimage', i, c)
         
        # width 와 height는 자유 파라미터로, 굳이 중요하지 않음.
        for i in train[start:end]:
            w, h = get_wh_from_filepath(i)
            self.add_image("openimage", image_id = i, path = i, width = w, height = h)
                
    def load_image(self, image_id):
        """Load the specified image and return a [H,W,3] Numpy array.
        """
        # Load image
        image = skimage.io.imread(self.image_info[image_id]['path'])
        # If grayscale. Convert to RGB for consistency.
        if image.ndim != 3:
            image = skimage.color.gray2rgb(image)
        # If has an alpha channel, remove it for consistency
        if image.shape[-1] == 4:
            image = image[..., :3]
        return image
    
    # override 
    def load_mask(self, id_num ) :
        
        file_name = self.image_info[id_num]['id']
        
        # 관련된 이미지 다 긁어옴.
        df_objects = get_objects_from_train_image(file_name.rsplit('.jpg')[0][-16:])
        
        class_ids = list()
        object_length = len(df_objects)
        mask = np.zeros([IMG_SIZE,IMG_SIZE, object_length], dtype= np.int8)
        
        # 하나라도 해당 물체가 발견되면 학습을 시작
        if object_length >= 1:
            
            m = skimage.io.imread(df_objects.iloc[0]['origin'])
            mask = np.zeros([m.shape[0], m.shape[1], object_length], dtype = np.int8) 
                
                
            # mask관련된 오브젝트 다 긁어옴
            for i,obj in enumerate(df_objects['object']) :
                       
                
                # 리사이즈를 해서 i번째 마스크에 할당
                mask[:,:,i] = skimage.io.imread(df_objects.iloc[i]['origin'])  
                
                class_candidate = class_list[class_list['object'] == obj]
                
                # 하나만 가져오면 되므로, 0번째를 가지고 오며 class id는 i와 동일.
                if len(class_candidate) >= 1 :
                    class_ids.append(class_candidate['image_index'].iloc[0])
            
        return mask.astype(np.bool), np.asarray(class_ids, dtype='int32')

    # 이 라이브러리는 image_info에 모든걸 저장해놓음.
    def image_info_list(self):
        print(self.image_info)
    
    def image_info(self, image_id):
        """Return the shapes data of the image."""
        return self.image_info[image_id]
                
dataset = DetectorDataset()
dataset.load_dataset(0, 700000) # train
dataset.prepare()

val_dataset = DetectorDataset()
val_dataset.load_dataset(700000, 808000) # validation
val_dataset.prepare()

ROOT_DIR = os.path.abspath("../../")

MODEL_DIR = os.path.join(ROOT_DIR, "logs")

COCO_MODEL_PATH = "mask_rcnn_coco.h5"

if not os.path.exists("mask_rcnn_coco.h5"):
    utils.download_trained_weights(COCO_MODEL_PATH)

class ShapesConfig(Config):
    """Configuration for training on the toy shapes dataset.
    Derives from the base Config class and overrides values specific
    to the toy shapes dataset.
    """
    # Give the configuration a recognizable name
    NAME = "shapes"

    # Train on 1 GPU and 8 images per GPU. We can put multiple images on each
    # GPU because the images are small. Batch size is 8 (GPUs * images/GPU).
    GPU_COUNT = 1
    IMAGES_PER_GPU = 6

    # Number of classes (including background)
    NUM_CLASSES = 351  

    # Use small images for faster training. Set the limits of the small side
    # the large side, and that determines the image shape.
    IMAGE_MIN_DIM = 256
    IMAGE_MAX_DIM = 256

    # Use smaller anchors because our image and objects are small
    RPN_ANCHOR_SCALES = (8, 16, 32, 64, 128)  # anchor side in pixels

    # Reduce training ROIs per image because the images are small and have
    # few objects. Aim to allow ROI sampling to pick 33% positive ROIs.
    TRAIN_ROIS_PER_IMAGE = 32

    # Use a small epoch since the data is simple
    STEPS_PER_EPOCH = 500 #700000 / IMAGES_PER_GPU

    # use small validation steps since the epoch is small
    VALIDATION_STEPS = 5
    
config = ShapesConfig()
config.display()

MODEL_DIR = os.path.join("./model/")

model = modellib.MaskRCNN(mode="training", config=config,model_dir=MODEL_DIR)

model.load_weights(COCO_MODEL_PATH, by_name=True,
                   exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox", "mrcnn_mask"])

model.train(dataset, val_dataset, learning_rate=0.01, epochs=10, layers='heads')

model.keras_model.save_weights("./my_mask_rcnn_all_tuning_head_size.h5")