def __getitem__(self, index):
ImageName = self.img_files[index]
I = cv2.imread(ImageName)
I = cv2.resize(I, (640, 640), interpolation=cv2.INTER_AREA)
#if(not np.shape(I2)):
# return
#cv2.imshow("I", I)
#cv2.waitKey()
I, ImageSize = iu.CenterCropFactor(I, self.Factor)
IS = iu.StandardizeInputs(np.float32(I))
Image = np.transpose(IS, (2, 0, 1))
MaskName = ImageName.replace("img", "mask")
#Image = cv2.imread(ImageName)
#RandImagePairName = self.img_files[index+1]
#Image, ImageSize = iu.CenterCropFactor(Image, self.Factor)
#Image = iu.StandardizeInputs(np.float32(Image))
mask = cv2.imread(MaskName)
if (not np.shape(mask)):
mask = np.zeros(ImageSize, dtype=np.int)
mask = cv2.resize(mask, (640, 640), interpolation=cv2.INTER_AREA)
else:
mask = cv2.resize(mask, (640, 640), interpolation=cv2.INTER_AREA)
#cv2.imshow("mask", mask)
#cv2.waitKey()
mask, _ = iu.CenterCropFactor(mask, self.Factor)
mask = np.float32(mask[:, :, 0]) / 255.0
mask = np.expand_dims(mask, axis=2)
mask = np.dstack((mask, 1.0 - mask))
#transform = transforms.Compose([transforms.ToTensor(), \
# transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
return Image, mask
def __getitem__(self, index):
ImageName = self.img_files[index]
#ImagePairName = self.img_files[index+1]
I = cv2.imread(ImageName)
#I2 = cv2.imread(ImagePairName)
#if(not np.shape(I2)):
# return
I, ImageSize = iu.CenterCropFactor(I, self.Factor)
#I2, _ = iu.CenterCropFactor(I2, self.Factor)
#ICombined = np.dstack((I1, I2)) # 沿第3维组合
IS = iu.StandardizeInputs(np.float32(I))
Image = np.transpose(IS, (2, 0, 1))
MaskName = ImageName.replace("img", "mask")
#Image = cv2.imread(ImageName)
#RandImagePairName = self.img_files[index+1]
#Image, ImageSize = iu.CenterCropFactor(Image, self.Factor)
#Image = iu.StandardizeInputs(np.float32(Image))
mask = cv2.imread(MaskName)
if (not np.shape(mask)):
mask = np.zeros(ImageSize, dtype=np.int)
#Mask2Name = ImagePairName.replace("img", "mask")
#mask2 = cv2.imread(Mask2Name)
#if (not np.shape(mask2)):
# mask2 = np.zeros(ImageSize, dtype=np.int)
mask, _ = iu.CenterCropFactor(mask, self.Factor)
mask = np.float32(mask[:, :, 0]) / 255.0
mask = np.expand_dims(mask, axis=2)
mask = np.dstack((mask, 1.0 - mask))
#transform = transforms.Compose([transforms.ToTensor(), \
# transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
return Image, mask
def SetupAll(BasePath, LearningRate):
"""
Inputs:
BasePath is the base path where Images are saved without "/" at the end
Outputs:
DirNames - Full path to all image files without extension
Train/Val/Test - Idxs of all the images to be used for training/validation (held-out testing in this case)/testing
Ratios - Ratios is a list of fraction of data used for [Train, Val, Test]
CheckPointPath - Path to save checkpoints/model
OptimizerParams - List of all OptimizerParams: depends on Optimizer
SaveCheckPoint - Save checkpoint every SaveCheckPoint iteration in every epoch, checkpoint saved automatically after every epoch
ImageSize - Size of the image
NumTrain/Val/TestSamples - length(Train/Val/Test)
NumTestRunsPerEpoch - Number of passes of Val data with MiniBatchSize
Train/Val/TestLabels - Labels corresponding to Train/Val/Test
"""
# Setup DirNames
DirNamesPath = BasePath + os.sep + 'DirNames.txt'
LabelNamesPath = BasePath + os.sep + 'Labels.txt'
TrainPath = BasePath + os.sep + 'Train.txt'
DirNames, TrainNames, TrainLabels = ReadDirNames(DirNamesPath,
LabelNamesPath, TrainPath)
# Setup Neural Net Params
# List of all OptimizerParams: depends on Optimizer
# For ADAM Optimizer: [LearningRate, Beta1, Beta2, Epsilion]
UseDefaultFlag = 0 # Set to 0 to use your own params, do not change default parameters
if UseDefaultFlag:
# Default Parameters
OptimizerParams = [1e-3, 0.9, 0.999, 1e-8]
else:
# Custom Parameters
OptimizerParams = [LearningRate, 0.9, 0.999, 1e-8]
# Save checkpoint every SaveCheckPoint iteration in every epoch, checkpoint saved automatically after every epoch
SaveCheckPoint = 100
# Image Input Shape
Factor = 3
I = cv2.imread(BasePath + os.sep + TrainNames[0])
_, ImageSize = iu.CenterCropFactor(I, Factor)
NumTrainSamples = len(TrainNames)
return TrainNames, TrainLabels, OptimizerParams, SaveCheckPoint, Factor, ImageSize, NumTrainSamples
def GenerateBatch(TrainNames, TrainLabels, Factor, ImageSize, MiniBatchSize,
BasePath, MaxFrameDiff):
"""
Inputs:
DirNames - Full path to all image files without extension
NOTE that Train can be replaced by Val/Test for generating batch corresponding to validation (held-out testing in this case)/testing
TrainLabels - Labels corresponding to Train
NOTE that TrainLabels can be replaced by Val/TestLabels for generating batch corresponding to validation (held-out testing in this case)/testing
ImageSize - Size of the Image
MiniBatchSize is the size of the MiniBatch
Outputs:
I1Batch - Batch of I1 images after standardization and cropping/resizing to ImageSize
HomeVecBatch - Batch of Homing Vector labels
"""
IBatch = []
I1Batch = []
I2Batch = []
LabelBatch = []
ImageNum = 0
while ImageNum < MiniBatchSize:
# Generate random image
RandIdx = random.randint(0, len(TrainNames) - MaxFrameDiff)
RandFrameDiff = random.randint(1, MaxFrameDiff)
RandImageName = TrainNames[RandIdx]
# Create File Number in same folder with RandFrameDiff
RandImagePairName = RandImageName.split(
os.sep)[0] + os.sep + 'events' + os.sep + 'event_' + str(
int(re.split('_|.png', RandImageName)[-2]) + RandFrameDiff)
I2 = cv2.imread(BasePath + os.sep + RandImagePairName + '.png')
if (not np.shape(I2)
): # OpenCV returns empty matrix if no image is found!
continue # Retry if RandImagePair is not valid!
I1 = cv2.imread(BasePath + os.sep + RandImageName)
ImageNum += 1
I1, _ = iu.CenterCropFactor(I1, Factor)
I2, _ = iu.CenterCropFactor(I2, Factor)
ICombined = np.dstack((I1, I2))
# Standardize Inputs as given by Inception v3 paper
# MAYBE: Find Mean of Dataset or use from ImageNet
# MAYBE: Normalize Dataset
# https://stackoverflow.com/questions/42275815/should-i-substract-imagenet-pretrained-inception-v3-model-mean-value-at-inceptio
IS = iu.StandardizeInputs(np.float32(ICombined))
Label1 = cv2.imread(BasePath + os.sep + TrainLabels[RandIdx])
Label1Name = TrainLabels[RandIdx]
Label2Name = Label1Name.split(
os.sep)[0] + os.sep + 'masks' + os.sep + 'mask_' + '%08d.png' % (
int(re.split('_|.png', RandImageName)[-2]) + RandFrameDiff
) # 08
Label2 = cv2.imread(BasePath + os.sep + Label2Name)
LabelCropped, _ = iu.CenterCropFactor(
Label1 | Label2,
Factor) # Label Mask is the logical OR of both Masks
LabelCropped = np.float32(LabelCropped[:, :, 0]) / 255.0
LabelCropped = np.expand_dims(LabelCropped, axis=3)
LabelCropped = np.dstack((LabelCropped, 1.0 - LabelCropped))
# Append All Images and Mask
IBatch.append(IS)
I1Batch.append(I1)
I2Batch.append(I2)
LabelBatch.append(LabelCropped)
return IBatch, I1Batch, I2Batch, LabelBatch
