import scipy #get the image path imagePath=sys.argv[1] #set output filename outName=sys.argv[2] #open the image image=Image.open(imagePath) #image as numpy array image=numpy.asarray(image) #keep only one dimension image=image[:,:,0] #most needed type casting image=image.astype(numpy.uint8) #crop the center image=myTools.cropCenter1(image, 83.1) #split image to 4 splits=myTools.augmentData(image.reshape(1,1,image.shape[0],image.shape[1]), numOfTiles=4, overlap=False, imageWidth=image.shape[0], imageHeight=image.shape[1]) #another vital type casting splits=splits.astype(numpy.float32) #keep only the 4 original tiles splits=splits[0:4,:,:,:] #setting parameters for the network data_size=(None,1,splits[0][0].shape[0],splits[0][0].shape[1]) #load the pretrained network myNet=myTools.createPretrainedNN(data_size) #make predictions for the 4 tiles print(splits.dtype) res=myNet(splits) #crop the center of the predictions res=myTools.cropCenter(res, 93)
from os import listdir from os.path import isfile, join from sklearn.metrics import mean_squared_error from math import sqrt #get the produced masks' path imagePath = sys.argv[1] #get all images' names filenames = [f for f in listdir(imagePath) if isfile(join(imagePath, f))] rmseList = list() for f in filenames: #open the image myMask = Image.open(imagePath + '/' + f, 'r') #image as numpy array myMask = numpy.asarray(myMask) myMask = myTools.cropCenter1(myMask, 100) #open the expert mask theMask = Image.open('../../masksExpertTest/' + '/' + f, 'r') #image as numpy array theMask = numpy.asarray(theMask) thisRMSE = sqrt(mean_squared_error(theMask, myMask)) rmseList.append(thisRMSE) print(numpy.mean(rmseList))
import scipy #get the image path imagePath = sys.argv[1] #set output filename outName = sys.argv[2] #open the image image = Image.open(imagePath) #image as numpy array image = numpy.asarray(image) #keep only one dimension image = image[:, :, 0] #most needed type casting image = image.astype(numpy.uint8) #crop the center image = myTools.cropCenter1(image, 100) #this step is mysteriously needed image = myTools.augmentMasks(image.reshape(1, 1, image.shape[0], image.shape[1]), numOfTiles=1, overlap=False, imageWidth=image.shape[0], imageHeight=image.shape[1]) #another vital type casting image = image.astype(numpy.float32) #setting parameters for the network data_size = (None, 1, image[0][0].shape[0], image[0][0].shape[1]) #load the pretrained network myNet = myTools.createPretrainedNN(data_size) #make predictions for the image res = myNet(image)
from sklearn.metrics import mean_squared_error from math import sqrt #get the produced masks' path imagePath=sys.argv[1] #get all images' names filenames = [f for f in listdir(imagePath) if isfile(join(imagePath, f))] rmseList=list() for f in filenames: #open the image myMask=Image.open(imagePath + '/' + f, 'r') #image as numpy array myMask=numpy.asarray(myMask) myMask=myTools.cropCenter1(myMask, 100) #open the expert mask theMask=Image.open('../../masksExpertTest/' + '/' + f, 'r') #image as numpy array theMask=numpy.asarray(theMask) thisRMSE = sqrt(mean_squared_error(theMask, myMask)) rmseList.append(thisRMSE) print(numpy.mean(rmseList))
#get the image path imagePath=sys.argv[1] #get the threshold level thresh=float(sys.argv[2]) #get the erosion shape er=int(sys.argv[3]) #open the image image=Image.open(imagePath) #image as numpy array image=numpy.asarray(image) #keep only one dimension image=image[:,:,0] #most needed type casting image=image.astype(numpy.uint8) #crop the center image=myTools.cropCenter1(image, 80) #split image to 4 splits=myTools.augmentMasks(image.reshape(1,1,image.shape[0],image.shape[1]), numOfTiles=4, overlap=False, imageWidth=image.shape[0], imageHeight=image.shape[1]) #another vital type casting splits=splits.astype(numpy.float32) #keep only the 4 original tiles splits=splits[0:4,:,:,:] #setting parameters for the network data_size=(None,1,splits[0][0].shape[0],splits[0][0].shape[1]) #load the pretrained network myNet=myTools.createPretrainedNN(data_size) #make predictions for the 4 tiles res=myNet(splits) #concatenate on the x axis top=np.concatenate((res[0][0],res[1][0]),axis=1) bot=np.concatenate((res[2][0],res[3][0]),axis=1)
import scipy #get the image path imagePath=sys.argv[1] #set output filename outName=sys.argv[2] #open the image image=Image.open(imagePath) #image as numpy array image=numpy.asarray(image) #keep only one dimension image=image[:,:,0] #most needed type casting image=image.astype(numpy.uint8) #crop the center image=myTools.cropCenter1(image, 100) #this step is mysteriously needed image=myTools.augmentMasks(image.reshape(1,1,image.shape[0],image.shape[1]), numOfTiles=1, overlap=False, imageWidth=image.shape[0], imageHeight=image.shape[1]) #another vital type casting image=image.astype(numpy.float32) #setting parameters for the network data_size=(None,1,image[0][0].shape[0],image[0][0].shape[1]) #load the pretrained network myNet=myTools.createPretrainedNN(data_size) #make predictions for the image res=myNet(image) #crop the center of the mask res=myTools.cropCenter(res, 80) plt.show(plt.imshow(res[0][0], cmap=cm.binary))