Changeset - db53fefbf557
Parent rev.
Child rev.
[Not reviewed]
default
0 4 1
Laman - 6 years ago 2019-06-09 21:10:09

Hakugen detection module
5 files changed with 87 insertions and 44 deletions:
exp/dochi.py
11
7
exp/exp_config.py
1
exp/hakugen.py
49
exp/kerokero/prepare_data.py
23
3
exp/kerokero/train.py
3
34
0 comments (0 inline, 0 general)
exp/dochi.py
➞
Show inline comments
 
import os
 
import time
 
import argparse
 
import logging as log
 

			




	
	
	
		
 
import cv2 as cv

			




	
	
	
		
 
import numpy as np

			




	
	
	
		
 
import keras

			




	
	
	
		
 
from keras.models import load_model

			




	
	
	
		
 
from PIL import Image,ImageDraw

			




	
	
	
		
 
from PIL import Image

			




	
	
	
		
 

			




	
	
	
		
 
from epoint import EPoint

			




	
	
	
		
 
import exp_config as cfg

			




	
	
	
		
 
from kerokero.k_util import averageDistance

			




	
	
	
		
 

			




	
	
	
		
 
keras.losses.averageDistance=averageDistance

			




	
	
	
		
 
keras.metrics.averageDistance=averageDistance

			




	
	
	
		
 

			




	
	
	
		
 
model=load_model(cfg.dochiModel)

			




	
	
	
		
 
SIDE=224

			




	
	
	
		
 

			




	
	
	
		
 

			




	
	
	
		
 
def locateGrid(img):

			




	
	
	
		
 
	t1=time.time()

			




	
	
	
		
 
	(width,height)=img.size

			




	
	
	
		
 
	normedImg=img.convert("L").resize((224,224),resample=Image.BILINEAR)

			




	
	
	
		
 
	npImg=np.array(normedImg.getdata()).reshape((224,224,1)).astype(np.float32)

			




	
	
	
		
 
	npImg=npImg/128-1

			




	
	
	
		
 

			




	
	
	
		
 
	label=model.predict(np.reshape(npImg,(1,224,224,1)))

			




	
	
	
		
 
	points=[]

			




	
	
	
		
 
	for i in range(4):

			




	
	
	
		
 
		points.append(EPoint((label[0][i][0]+1)*(width/2),(label[0][i][1]+1)*(height/2)))

			




	
	
	
		
 
		points.append([(label[0][i][0]+1)*(width/2),(label[0][i][1]+1)*(height/2)])

			




	
	
	
		
 
	t=time.time()-t1

			




	
	
	
		
 
	log.info("grid located in {0:.3}s".format(t))

			




	
	
	
		
 
	return points

			




	
	
	
		
 

			




	
	
	
		
 

			




	
	
	
		
 
if __name__=="__main__":

			




	
	
		
 
@@ -40,10 +41,13 @@ if __name__=="__main__":

			




	
	
	
		
 
	parser.add_argument("-o","--output_dir",required=True)

			




	
	
	
		
 
	args=parser.parse_args()

			




	
	
	
		
 

			




	
	
	
		
 
	for image_path in args.input:

			




	
	
	
		
 
		image=Image.open(image_path)

			




	
	
	
		
 
		points=locateGrid(image)

			




	
	
	
		
 
		drawer=ImageDraw.Draw(image)

			




	
	
	
		
 
		for p in points:

			




	
	
	
		
 
			drawer.ellipse((p.x-2,p.y-2,p.x+2,p.y+2),fill="#00ff00")

			




	
	
	
		
 
		image.save(os.path.join(args.output_dir,os.path.basename(image_path)))

			




	
	
	
		
 
		x1=SIDE*0.1

			




	
	
	
		
 
		x2=SIDE*0.9

			




	
	
	
		
 
		destPoints=[(x1,x1),(x1,x2),(x2,x2),(x2,x1)]

			




	
	
	
		
 
		m=cv.getPerspectiveTransform(np.float32(points),np.float32(destPoints))

			




	
	
	
		
 
		img=cv.warpPerspective(np.uint8(image),m,(SIDE,SIDE))

			




	
	
	
		
 
		img=cv.cvtColor(img,cv.COLOR_BGR2RGB)

			




	
	
	
		
 
		cv.imwrite(os.path.join(args.output_dir,os.path.basename(image_path)),img)

			




        

    


    
    

    

        

                

                    exp/exp_config.py
                

                

                  
                      
                        

                      ➞

                      
                        
                  

                  
                      
                  
                      
                  
                      
                  
                      
                  
                  
                

                

                    Show inline comments
                    
                

        

        

            



	
	
		
 
@@ -10,10 +10,11 @@ with open(os.path.join(thisDir,"config.j

			




	
	
	
		
 
	cfg=json.load(f)

			




	
	
	
		
 

			




	
	
	
		
 
INTERACTIVE=False

			




	
	
	
		
 
imgDir="/tmp/oneEye"

			




	
	
	
		
 
sansaModel=cfg.get("sansaModel")

			




	
	
	
		
 
dochiModel=cfg.get("dochiModel")

			




	
	
	
		
 
hakugenModel=cfg.get("hakugenModel")

			




	
	
	
		
 
i=1

			




	
	
	
		
 

			




	
	
	
		
 
if not os.path.exists(imgDir):

			




	
	
	
		
 
	os.mkdir(imgDir)

			




        

    


    
    

    

        

                

                    exp/hakugen.py
                

                

                  
                      
                        

                      ➞

                      
                        
                  

                  
                      
                  
                      
                  
                      
                  
                      
                  
                  
                

                

                    Show inline comments
                    
                

        

        

            



	
	
		
 
new file 100644

			




	
	
	
		
 
import os

			




	
	
	
		
 
import time

			




	
	
	
		
 
import argparse

			




	
	
	
		
 
import logging as log

			




	
	
	
		
 

			




	
	
	
		
 
import numpy as np

			




	
	
	
		
 
import keras

			




	
	
	
		
 
from keras.models import load_model

			




	
	
	
		
 
from PIL import Image,ImageDraw

			




	
	
	
		
 

			




	
	
	
		
 
from epoint import EPoint

			




	
	
	
		
 
import exp_config as cfg

			




	
	
	
		
 
from kerokero.k_util import averageDistance

			




	
	
	
		
 

			




	
	
	
		
 
keras.losses.averageDistance=averageDistance

			




	
	
	
		
 
keras.metrics.averageDistance=averageDistance

			




	
	
	
		
 

			




	
	
	
		
 
model=load_model(cfg.hakugenModel)

			




	
	
	
		
 

			




	
	
	
		
 

			




	
	
	
		
 
def locateGrid(img):

			




	
	
	
		
 
	t1=time.time()

			




	
	
	
		
 
	(width,height)=img.size

			




	
	
	
		
 
	normedImg=img.convert("L")

			




	
	
	
		
 
	npImg=np.array(normedImg.getdata()).reshape((224,224,1)).astype(np.float32)

			




	
	
	
		
 
	npImg=npImg/128-1

			




	
	
	
		
 

			




	
	
	
		
 
	label=model.predict(np.reshape(npImg,(1,224,224,1)))

			




	
	
	
		
 
	points=[]

			




	
	
	
		
 
	for i in range(4):

			




	
	
	
		
 
		points.append(EPoint((label[0][i][0]+1)*(width/2),(label[0][i][1]+1)*(height/2)))

			




	
	
	
		
 
	t=time.time()-t1

			




	
	
	
		
 
	log.info("grid located in {0:.3}s".format(t))

			




	
	
	
		
 
	return points

			




	
	
	
		
 

			




	
	
	
		
 

			




	
	
	
		
 
if __name__=="__main__":

			




	
	
	
		
 
	parser=argparse.ArgumentParser()

			




	
	
	
		
 
	parser.add_argument("-i","--input",nargs="+")

			




	
	
	
		
 
	parser.add_argument("-o","--output_dir",required=True)

			




	
	
	
		
 
	args=parser.parse_args()

			




	
	
	
		
 

			




	
	
	
		
 
	for image_path in args.input:

			




	
	
	
		
 
		image=Image.open(image_path)

			




	
	
	
		
 
		points=locateGrid(image)

			




	
	
	
		
 
		drawer=ImageDraw.Draw(image)

			




	
	
	
		
 
		for p in points:

			




	
	
	
		
 
			drawer.ellipse((p.x-2,p.y-2,p.x+2,p.y+2),fill="#00ff00")

			




	
	
	
		
 
		image.save(os.path.join(args.output_dir,os.path.basename(image_path)))

			




        

    


    
    

    

        

                

                    exp/kerokero/prepare_data.py
                

                

                  
                      
                        

                      ➞

                      
                        
                  

                  
                      
                  
                      
                  
                      
                  
                      
                  
                  
                

                

                    Show inline comments
                    
                

        

        

            



	
	
	
		
 
import os

			




	
	
	
		
 
import sys

			




	
	
	
		
 
import re

			




	
	
	
		
 
import math

			




	
	
	
		
 
import random

			




	
	
	
		
 
import logging as log

			




	
	
	
		
 

			




	
	
	
		
 
import numpy as np

			




	
	
	
		
 
import cv2 as cv

			




	
	
	
		
 

			




	
	
		
 
@@ -45,12 +46,25 @@ class Sample:

			




	
	
	
		
 
		img=cv.warpPerspective(self.img,m,(self.SIDE,self.SIDE))

			




	
	
	
		
 
		img=np.uint8(img)

			




	
	
	
		
 
		grid=Corners(c.transform(m) for c in self.grid)

			




	
	
	
		
 
		grid=list(map(lambda p: list(2*p/self.SIDE-EPoint(1,1)), grid))

			




	
	
	
		
 
		return (img,grid)

			




	
	
	
		
 

			




	
	
	
		
 
	def rectify(self):

			




	
	
	
		
 
		x1=self.SIDE*0.1

			




	
	
	
		
 
		x2=self.SIDE*0.9

			




	
	
	
		
 
		abcd=list(map(list,self.grid))

			




	
	
	
		
 
		destPoints=[(x1,x1),(x1,x2),(x2,x2),(x2,x1)]

			




	
	
	
		
 
		abcd_=list(map(list, (EPoint(x,y)+self._createNoise() for (x,y) in destPoints)))

			




	
	
	
		
 
		m=cv.getPerspectiveTransform(np.float32(abcd),np.float32(abcd_))

			




	
	
	
		
 
		img=cv.warpPerspective(self.img,m,(self.SIDE,self.SIDE))

			




	
	
	
		
 
		img=np.uint8(img)

			




	
	
	
		
 
		grid=Corners(c.transform(m) for c in self.grid)

			




	
	
	
		
 
		grid=list(map(lambda p: list(2*p/self.SIDE-EPoint(1,1)), grid))

			




	
	
	
		
 
		return (img,grid)

			




	
	
	
		
 

			




	
	
	
		
 
	def _getCenter(self):

			




	
	
	
		
 
		(a,b,c,d)=self.grid

			




	
	
	
		
 
		p=Line.fromPoints(a,c)

			




	
	
	
		
 
		q=Line.fromPoints(b,d)

			




	
	
	
		
 
		return p.intersect(q)

			




	
	
	
		
 

			




	
	
		
 
@@ -60,12 +74,17 @@ class Sample:

			




	
	
	
		
 
		(wg,hg)=(x2-x1,y2-y1)

			




	
	
	
		
 
		(left,top,right,bottom)=[random.uniform(0.05,0.2) for i in range(4)]

			




	
	
	
		
 
		t2=getTranslation(left*wg-x1, top*hg-y1)

			




	
	
	
		
 
		scale=getScale(self.SIDE/(wg*(1+left+right)), self.SIDE/(hg*(1+top+bottom)))

			




	
	
	
		
 
		return np.matmul(scale,t2)

			




	
	
	
		
 

			




	
	
	
		
 
	def _createNoise(self):

			




	
	
	
		
 
		alpha=random.uniform(0,math.pi*2)

			




	
	
	
		
 
		d=random.uniform(0,self.SIDE*0.05)

			




	
	
	
		
 
		return EPoint(math.cos(alpha)*d, math.sin(alpha)*d)

			




	
	
	
		
 

			




	
	
	
		
 
	def show(self):

			




	
	
	
		
 
		img=cv.cvtColor(self.img,cv.COLOR_GRAY2BGR)

			




	
	
	
		
 
		for c in self.grid:

			




	
	
	
		
 
			cv.circle(img,(int(c.x),int(c.y)),3,[0,255,0],-1)

			




	
	
	
		
 
		img=cv.resize(img,(self.SIDE*2,self.SIDE*2))

			




	
	
	
		
 
		show(img)

			




	
	
		
 
@@ -88,20 +107,21 @@ def harvestDir(path):

			




	
	
	
		
 
	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:

			




	
	
	
		
 
		grade=annotations.get(f.name,[Board()])[0].grade

			




	
	
	
		
 
		Stats.counts[grade]+=1

			




	
	
	
		
 
		if not Board.UNSET<grade<=Board.POOR: continue

			




	
	
	
		
 
		if not Board.UNSET<grade<=Board.GOOD: continue

			




	
	
	
		
 
		img=cv.imread(f.path)

			




	
	
	
		
 
		img=cv.cvtColor(img,cv.COLOR_BGR2GRAY)

			




	
	
	
		
 
		for b in boards:

			




	
	
	
		
 
			sample=Sample(img,b.grid)

			




	
	
	
		
 
			# sample.show()

			




	
	
	
		
 
			(transformedImg,label)=sample.transform()

			




	
	
	
		
 
			# Sample(np.uint8((transformedImg+1)*128),map(lambda c: (c+EPoint(1,1))*Sample.SIDE/2,transformedGrid)).show()

			




	
	
	
		
 
			# (transformedImg,label)=sample.transform()

			




	
	
	
		
 
			(transformedImg,label)=sample.rectify()

			




	
	
	
		
 
			# Sample(np.uint8(transformedImg),map(lambda c: (EPoint(*c)+EPoint(1,1))*Sample.SIDE/2,label)).show()

			




	
	
	
		
 
			yield (transformedImg,label)

			




	
	
	
		
 

			




	
	
	
		
 

			




	
	
	
		
 
def loadDataset(root):

			




	
	
	
		
 
	testRatio=0.1

			




	
	
	
		
 
	trainRatio=1-testRatio

			




        

    


    
    

    

        

                

                    exp/kerokero/train.py
                

                

                  
                      
                        

                      ➞

                      
                        
                  

                  
                      
                  
                      
                  
                      
                  
                      
                  
                  
                

                

                    Show inline comments
                    
                

        

        

            



	
	
		
 
@@ -2,14 +2,14 @@ import os

			




	
	
	
		
 
import math

			




	
	
	
		
 
from time import time

			




	
	
	
		
 
import argparse

			




	
	
	
		
 
import logging as log

			




	
	
	
		
 

			




	
	
	
		
 
import numpy as np

			




	
	
	
		
 
from keras.layers import Conv2D,Dropout,Dense,Flatten,MaxPooling2D,BatchNormalization,GlobalAveragePooling2D,Reshape,concatenate

			




	
	
	
		
 
from keras.models import Sequential,load_model,Model,Input

			




	
	
	
		
 
from keras.layers import Conv2D,Dropout,Dense,Flatten,MaxPooling2D,BatchNormalization,GlobalAveragePooling2D,Reshape

			




	
	
	
		
 
from keras.models import Sequential,load_model

			




	
	
	
		
 
from keras.callbacks import TensorBoard,ModelCheckpoint

			




	
	
	
		
 
import keras.metrics

			




	
	
	
		
 

			




	
	
	
		
 
import config as cfg

			




	
	
	
		
 
from k_util import averageDistance,generateData

			




	
	
	
		
 

			




	
	
		
 
@@ -70,47 +70,16 @@ def createCNN():

			




	
	
	
		
 
	model.add(Reshape((4,2)))

			




	
	
	
		
 

			




	
	
	
		
 
	model.compile(optimizer="rmsprop",loss=averageDistance,metrics=["mae","accuracy"])

			




	
	
	
		
 
	return model

			




	
	
	
		
 

			




	
	
	
		
 

			




	
	
	
		
 
def createHinted():

			




	
	
	
		
 
	input=Input((224,224,1))

			




	
	
	
		
 
	base=load_model(args.load_hints)

			




	
	
	
		
 
	for layer in base.layers:

			




	
	
	
		
 
		layer.trainable=False

			




	
	
	
		
 
	hints=base(input)

			




	
	
	
		
 

			




	
	
	
		
 
	x=BatchNormalization()(input)

			




	
	
	
		
 
	x=Conv2D(24,(5,5),padding="same",kernel_initializer="he_normal",activation="relu",input_shape=(224,224,1),data_format="channels_last")(x)

			




	
	
	
		
 
	x=MaxPooling2D(pool_size=(2,2),strides=(2,2),padding="valid")(x)

			




	
	
	
		
 
	x=Conv2D(36,(5,5),activation="relu")(x)

			




	
	
	
		
 
	x=MaxPooling2D(pool_size=(2,2),strides=(2,2),padding="valid")(x)

			




	
	
	
		
 
	x=Conv2D(48,(5,5),activation="relu")(x)

			




	
	
	
		
 
	x=MaxPooling2D(pool_size=(2,2),strides=(2,2),padding="valid")(x)

			




	
	
	
		
 
	x=Conv2D(64,(3,3),activation="relu")(x)

			




	
	
	
		
 
	x=MaxPooling2D(pool_size=(2,2),strides=(2,2),padding="valid")(x)

			




	
	
	
		
 
	x=Conv2D(64,(3,3),activation="relu")(x)

			




	
	
	
		
 
	x=GlobalAveragePooling2D()(x)

			




	
	
	
		
 

			




	
	
	
		
 
	x=concatenate([x,Flatten()(hints)])

			




	
	
	
		
 
	x=Dense(500,activation="relu")(x)

			




	
	
	
		
 
	x=Dense(90,activation="relu")(x)

			




	
	
	
		
 

			




	
	
	
		
 
	predictions=Reshape((4,2))(Dense(8)(x))

			




	
	
	
		
 

			




	
	
	
		
 
	model=Model(inputs=input,outputs=predictions)

			




	
	
	
		
 

			




	
	
	
		
 
	model.compile(optimizer='rmsprop',loss=averageDistance,metrics=['mae','accuracy'])

			




	
	
	
		
 
	return model

			




	
	
	
		
 

			




	
	
	
		
 

			




	
	
	
		
 
if args.load_model:

			




	
	
	
		
 
	model=load_model(args.load_model)

			




	
	
	
		
 
else:

			




	
	
	
		
 
	model=createHinted()

			




	
	
	
		
 
	model=createCNN()

			




	
	
	
		
 
	model.summary()

			




	
	
	
		
 

			




	
	
	
		
 
log.info("loading data...")

			




	
	
	
		
 
with np.load(args.data) as data:

			




	
	
	
		
 
	trainImages=(np.float32(data["trainImages"])/128-1).reshape((-1,224,224,1))

			




	
	
	
		
 
	trainLabels=data["trainLabels"].reshape((-1,4,2))

			




        

    



    


    



    



      

      





    
    0 comments (0 inline, 0 general)
    





    


  

  







  


    




    








    
        Server instance: Sirius-560
    
    
        This site is powered by
            Kallithea 0.7.0,
        which is
        © 2010–2023 by various authors & licensed under GPLv3.
            – Support