Changeset - 8b30e6dba468
[Not reviewed]
default
0 1 0
Laman - 6 years ago 2019-05-05 17:55:18

fix: corrupted training data
1 file changed with 2 insertions and 2 deletions:
0 comments (0 inline, 0 general)
exp/kerokero/prepare_data.py
Show inline comments
 
@@ -36,88 +36,88 @@ class Sample:
 
		img=cv.warpPerspective(self.img,m,(self.SIDE,self.SIDE))
 
		grid=Corners(c.transform(m) for c in self.grid)
 
		return (img,list(itertools.chain.from_iterable(grid)))
 

	
 
	def _getCenter(self):
 
		(a,b,c,d)=self.grid
 
		p=Line.fromPoints(a,c)
 
		q=Line.fromPoints(b,d)
 
		return p.intersect(q)
 

	
 
	def _computeCrop(self,m):
 
		grid=Corners(c.transform(m) for c in self.grid)
 
		(x1,y1,x2,y2)=computeBoundingBox(grid)
 
		(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 show(self):
 
		img=np.copy(self.img)
 
		for c in self.grid:
 
			cv.circle(img,(int(c.x),int(c.y)),3,[0,255,0],-1)
 
		show(img)
 

	
 

	
 
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)
 
		img=cv.cvtColor(img,cv.COLOR_BGR2GRAY)
 
		for b in boards:
 
			sample=Sample(img,b.grid)
 
			(img,label)=sample.transform()
 
			yield (img,label)
 
			(transformedImg,label)=sample.transform()
 
			yield (transformedImg,label)
 

	
 

	
 
def loadDataset(root):
 
	testRatio=0.1
 
	trainRatio=1-testRatio
 
	images=[]
 
	labels=[]
 
	for d in traverseDirs(root):
 
		for (img,label) in harvestDir(d):
 
			images.append(img)
 
			labels.append(label)
 
	n=len(images)
 
	keys=list(range(n))
 
	random.shuffle(keys)
 
	images=[images[k] for k in keys]
 
	labels=[labels[k] for k in keys]
 
	m=int(n*trainRatio)
 
	return (
 
		(np.uint8(images[:m]),np.float32(labels[:m])),
 
		(np.uint8(images[m:]),np.float32(labels[m:]))
 
	)
 

	
 

	
 
def show(img,filename="x"):
 
	cv.imshow(filename,img)
 
	cv.waitKey(0)
 
	cv.destroyAllWindows()
 

	
 

	
 
if __name__=="__main__":
 
	((trainImages,trainLabels),(testImages,testLabels))=loadDataset(sys.argv[1])
 
	np.savez_compressed(
 
		sys.argv[2],
 
		trainImages=trainImages,
 
		trainLabels=trainLabels,
 
		testImages=testImages,
 
		testLabels=testLabels
 
	)
0 comments (0 inline, 0 general)