import os

import sys

import re

import random

import cv2 as cv

sys.path.append("../exp")

from annotations import DataFile,computeBoundingBox

random.seed(361)

def traverseDirs(root):

	stack=[root]

	while len(stack)>0:

		d=stack.pop()

		contents=sorted(os.scandir(d),key=lambda f: f.name,reverse=True)

		if any(f.name=="annotations.json.gz" for f in contents):

			print(d)

			yield d

		for f in contents:

			if f.is_dir(): stack.append(f.path)

def harvestDir(path):

	annotations=DataFile(os.path.join(path,"annotations.json.gz"))

	imgFilter=lambda f: f.is_file() and re.match(r".*\.(jpg|jpeg|png|gif)$", f.name.lower())

	files=sorted(filter(imgFilter,os.scandir(path)),key=lambda f: f.name)

	boards=annotations["."]

	for f in files:

		img=cv.imread(f.path)

		for b in boards:

			crop(img,b)

def crop(img,board):

	margin=0.2

	(hi,wi)=img.shape[:2]

	(x1,y1,x2,y2)=computeBoundingBox(board.board)

	(wb,hb)=(x2-x1,y2-y1)

	dx1=min(int(wb*margin),x1)

	dx2=min(int(wb*margin),wi-x2)

	dy1=min(int(hb*margin),y1)

	dy2=min(int(hb*margin),hi-y2)

	xa=x1-random.randint(0,dx1)

	xb=x2+random.randint(0,dx2)

	ya=y1-random.randint(0,dy1)

	yb=y2+random.randint(0,dy2)

	show(img[ya:yb,xa:xb])

	return img[ya:yb,xa:xb]

def show(img,filename="x"):

	cv.imshow(filename,img)

	cv.waitKey(0)

	cv.destroyAllWindows()

if __name__=="__main__":

	root=sys.argv[1]

	for d in traverseDirs(root):

		harvestDir(d)

from keras.layers import Conv2D,Dropout,Dense,Flatten

from keras.models import Sequential

model = Sequential([

	Flatten(input_shape=(96,96)),

	Dense(128, activation="relu"),

	Dropout(0.1),

	Dense(64, activation="relu"),

	Dense(30)

])

model.compile(

	optimizer='adam',

	loss='mse',

	metrics=['mae','accuracy']

)

model.fit(X_train,y_train,epochs = 500,batch_size = 128,validation_split = 0.2)

export PYTHONPATH=${PYTHONPATH}:/home/laman/Programy/tensorflow/models/research/:/home/laman/Programy/tensorflow/models/research/slim

python export_inference_graph.py --input_type=image_tensor --pipeline_config_path=../models/model/ssd_mobilenet_v2_coco.config --trained_checkpoint_prefix=../models/model/model.ckpt-360 --output_directory=/tmp/nn3

# ffmpeg -i video.mp4 -r 1/10 out-dir/frame-%04d.jpg