def __readImages(self, filename):
image_string = tf.read_file(
filename) #Gets a string tensor from a file
decodedInput = tf.image.decode_image(
image_string) #Decode a string tensor as image
floatInput = tf.image.convert_image_dtype(
decodedInput, dtype=tf.float32) #Transform image to float32
assertion = tf.assert_equal(tf.shape(floatInput)[-1],
3,
message="image does not have 3 channels")
with tf.control_dependencies([assertion]):
floatInput.set_shape([None, None, 3])
gammadInput = floatInput
#print("CAREFUL THE GAMMA IS NOT CORRECTED AUTOMATICALLY")
#input = floatInput
input = tf.pow(floatInput, 2.2) #correct for the gamma
#If we want to log the inputs, we do it here
if self.logInput:
input = helpers.logTensor(input)
#The preprocess function puts the vectors value between [-1; 1] from [0;1]
input = helpers.preprocess(input)
targets = tf.zeros(tf.shape(input)) # is here (None, None, 3)
targets = tf.expand_dims(targets, axis=0)
targets = tf.tile(targets, (self.nbTargetsToRead, 1, 1, 1))
return filename, input, targets, gammadInput
def __readImages(self, filename):
image_string = tf.read_file(
filename) #Gets a string tensor from a file
decodedInput = tf.image.decode_image(
image_string) #Decode a string tensor as image
floatInput = tf.image.convert_image_dtype(
decodedInput, dtype=tf.float32) #Transform image to float32
assertion = tf.assert_equal(tf.shape(floatInput)[-1],
3,
message="image does not have 3 channels")
with tf.control_dependencies([assertion]):
floatInput.set_shape([None, None, 3])
inputShape = floatInput.get_shape()
if self.mode == "eval": #If the inputs are only the number of pictures declared
blackTargets = tf.zeros([
self.inputImageSize,
self.inputImageSize * self.nbTargetsToRead, 3
])
floatInput = tf.concat([floatInput, blackTargets], axis=1)
floatInputSplit = tf.split(
floatInput,
self.nbTargetsToRead + self.inputNumbers,
axis=1,
name="Split_input_data"
) #Splitted we get a list of nbTargets + inputNumbers images
#Sets the inputs and outputs depending on the order of images
if self.which_direction == "AtoB":
inputs = floatInputSplit[:self.inputNumbers]
targets = floatInputSplit[self.inputNumbers:]
elif self.which_direction == "BtoA":
inputs = floatInputSplit[self.inputNumbers:]
targets = floatInputSplit[:self.inputNumbers]
else:
raise ValueError("Invalid direction")
gammadInputs = inputs
inputs = [tf.pow(input, 2.2)
for input in inputs] #correct for the gamma
#If we want to log the inputs, we do it here
if self.logInput:
inputs = [helpers.logTensor(input) for input in inputs]
#The preprocess function puts the vectors value between [-1; 1] from [0;1]
inputs = [helpers.preprocess(input) for input in inputs]
#gammadInputs = [helpers.preprocess(gammadInput) for gammadInput in gammadInputs]
targets = [helpers.preprocess(target) for target in targets]
#We used to resize inputs and targets here, we have no functional need for it. Will see if there is a technical need to define the actual size.
return filename, inputs, targets, gammadInputs
def __renderInputs(self, materials, renderingScene, jitterLightPos, jitterViewPos, mixMaterials):
fullSizeMixedMaterial = materials
if mixMaterials:
alpha = tf.random_uniform([1], minval=0.1, maxval=0.9, dtype=tf.float32, name="mixAlpha")
materials1 = materials[::2]
materials2 = materials[1::2]
fullSizeMixedMaterial = helpers.mixMaterials(materials1, materials2, alpha)
if self.inputImageSize >= self.tileSize :
if self.fixCrop:
xyCropping = (self.inputImageSize - self.tileSize) // 2
xyCropping = [xyCropping, xyCropping]
else:
xyCropping = tf.random_uniform([2], 0, self.inputImageSize - self.tileSize, dtype=tf.int32)
cropped_mixedMaterial = fullSizeMixedMaterial[:,:, xyCropping[0] : xyCropping[0] + self.tileSize, xyCropping[1] : xyCropping[1] + self.tileSize, :]
elif self.inputImageSize < self.tileSize:
raise Exception("Size of the input is inferior to the size of the rendering, please provide higher resolution maps")
cropped_mixedMaterial.set_shape([None, self.nbTargetsToRead, self.tileSize, self.tileSize, 3])
mixedMaterial = helpers.adaptRougness(cropped_mixedMaterial)
targetstoRender = helpers.target_reshape(mixedMaterial) #reshape it to be compatible with the rendering algorithm [?, size, size, 12]
nbRenderings = 1
rendererInstance = renderer.GGXRenderer(includeDiffuse = True)
## Do renderings of the mixedMaterial
targetstoRender = helpers.preprocess(targetstoRender) #Put targets to -1; 1
surfaceArray = helpers.generateSurfaceArray(self.tileSize)
inputs = helpers.generateInputRenderings(rendererInstance, targetstoRender, self.batchSize, nbRenderings, surfaceArray, renderingScene, jitterLightPos, jitterViewPos, self.useAmbientLight, useAugmentationInRenderings = self.useAugmentationInRenderings)
self.gammaCorrectedInputsBatch = tf.squeeze(inputs, [1])
inputs = tf.pow(inputs, 2.2) # correct gamma
if self.logInput:
inputs = helpers.logTensor(inputs)
inputs = helpers.preprocess(inputs) #Put inputs to -1; 1
targets = helpers.target_deshape(targetstoRender, self.nbTargetsToRead)
return targets, inputs
def __renderInputs(self, materials, renderingScene, jitterLightPos,
jitterViewPos, mixMaterials, isTest, renderSize):
mixedMaterial = materials
if mixMaterials:
alpha = tf.random_uniform([1],
minval=0.1,
maxval=0.9,
dtype=tf.float32,
name="mixAlpha")
#print("mat2: " + str(materials2))
materials1 = materials[::2]
materials2 = materials[1::2]
mixedMaterial = helpers.mixMaterials(materials1, materials2, alpha)
mixedMaterial.set_shape(
[None, self.nbTargetsToRead, renderSize, renderSize, 3])
mixedMaterial = helpers.adaptRougness(mixedMaterial)
#These 3 lines below tries to scale the albedos to get more variety and to randomly flatten the normals to disambiguate the normals and albedos. We did not see strong effect for these.
#if not isTest and self.useAugmentationInRenderings:
# mixedMaterial = helpers.adaptAlbedos(mixedMaterial, self.batchSize)
# mixedMaterial = helpers.adaptNormals(mixedMaterial, self.batchSize)
reshaped_targets_batch = helpers.target_reshape(
mixedMaterial
) #reshape it to be compatible with the rendering algorithm [?, size, size, 12]
nbRenderings = self.maxInputToRead
if not self.fixImageNb:
#If we don't want a constant number of input images, we randomly select a number of input images between 1 and the maximum number of images defined by the user.
nbRenderings = tf.random_uniform([1],
1,
self.maxInputToRead + 1,
dtype=tf.int32)[0]
rendererInstance = renderer.GGXRenderer(includeDiffuse=True)
## Do renderings of the mixedMaterial
targetstoRender = reshaped_targets_batch
pixelsToAdd = 0
targetstoRender = helpers.preprocess(
targetstoRender) #Put targets to -1; 1
surfaceArray = helpers.generateSurfaceArray(
renderSize, pixelsToAdd
) #Generate a grid Y,X between -1;1 to act as the pixel support of the rendering (computer the direction vector between each pixel and the light/view)
#Do the renderings
inputs = helpers.generateInputRenderings(
rendererInstance,
targetstoRender,
self.batchSize,
nbRenderings,
surfaceArray,
renderingScene,
jitterLightPos,
jitterViewPos,
self.useAmbientLight,
useAugmentationInRenderings=self.useAugmentationInRenderings)
#inputs = [helpers.preprocess(input) for input in inputs]
randomTopLeftCrop = tf.zeros([self.batchSize, nbRenderings, 2],
dtype=tf.int32)
averageCrop = 0.0
#If we want to jitter the renderings around (to try to take into account small non alignment), we should handle the material crop a bit differently
#We didn't really manage to get satisfying results with the jittering of renderings. But the code could be useful if this is of interest to Ansys.
if self.jitterRenderings:
randomTopLeftCrop = tf.random_normal(
[self.batchSize, nbRenderings, 2], 0.0,
1.0) #renderSize - self.cropSize, dtype=tf.int32)
randomTopLeftCrop = randomTopLeftCrop * tf.exp(
tf.random_normal(
[self.batchSize], 0.0,
1.0)) #renderSize - self.cropSize, dtype=tf.int32)
randomTopLeftCrop = randomTopLeftCrop - tf.reduce_mean(
randomTopLeftCrop, axis=1, keep_dims=True)
randomTopLeftCrop = tf.round(randomTopLeftCrop)
randomTopLeftCrop = tf.cast(randomTopLeftCrop, dtype=tf.int32)
averageCrop = tf.cast(self.maxJitteringPixels * 0.5,
dtype=tf.int32)
randomTopLeftCrop = randomTopLeftCrop + averageCrop
randomTopLeftCrop = tf.clip_by_value(randomTopLeftCrop, 0,
self.maxJitteringPixels)
totalCropSize = self.cropSize
inputs, targets = helpers.cutSidesOut(inputs, targetstoRender,
randomTopLeftCrop, totalCropSize,
self.firstAsGuide, averageCrop)
print("inputs shape after" + str(inputs.get_shape()))
self.gammaCorrectedInputsBatch = inputs
tf.summary.image("GammadInputs",
helpers.convert(inputs[0, :]),
max_outputs=5)
inputs = tf.pow(inputs, 2.2) # correct gamma
if self.logInput:
inputs = helpers.logTensor(inputs)
inputs = helpers.preprocess(inputs)
targets = helpers.target_deshape(targets, self.nbTargetsToRead)
return targets, inputs
def populateInNetworkFeedGraphSpatialMix(self,
renderingScene,
shuffle=True,
imageSize=512,
useSpatialMix=True):
with tf.name_scope("load_images"):
#Create a tensor out of the list of paths
filenamesTensor = tf.constant(self.pathList)
#Reads a slice of the tensor, for example, if the tensor is of shape [100,2], the slice shape should be [2] (to check if we have problem here)
dataset = tf.data.Dataset.from_tensor_slices(filenamesTensor)
#for each slice apply the __readImages function
dataset = dataset.map(self.__readImagesGT,
num_parallel_calls=int(
multiprocessing.cpu_count() / 4))
#Authorize repetition of the dataset when one epoch is over.
#shuffle = True
if shuffle:
dataset = dataset.shuffle(buffer_size=16,
reshuffle_each_iteration=True)
#set batch size
dataset = dataset.repeat()
toPull = self.batchSize
if useSpatialMix:
toPull = self.batchSize * 2
batched_dataset = dataset.batch(toPull)
batched_dataset = batched_dataset.prefetch(buffer_size=4)
#Create an iterator to be initialized
iterator = batched_dataset.make_initializable_iterator()
#Create the node to retrieve next batch
paths_batch, targets_batch = iterator.get_next()
inputRealSize = imageSize #Should be input image size but changed tmp
if useSpatialMix:
threshold = 0.5
perlinNoise = tf.expand_dims(tf.expand_dims(
helpers.generate_perlin_noise_2d(
(inputRealSize, inputRealSize), (1, 1)),
axis=-1),
axis=0)
perlinNoise = (perlinNoise + 1.0) * 0.5
perlinNoise = perlinNoise >= threshold
perlinNoise = tf.cast(perlinNoise, tf.float32)
inverted = 1.0 - perlinNoise
materialsMixed1 = targets_batch[::2] * perlinNoise
materialsMixed2 = targets_batch[1::2] * inverted
fullSizeMixedMaterial = materialsMixed1 + materialsMixed2
targets_batch = fullSizeMixedMaterial
paths_batch = paths_batch[::2]
targetstoRender = helpers.target_reshape(
targets_batch
) #reshape it to be compatible with the rendering algorithm [?, size, size, 12]
nbRenderings = 1
rendererInstance = renderer.GGXRenderer(includeDiffuse=True)
## Do renderings of the mixedMaterial
mixedMaterial = helpers.adaptRougness(targetstoRender)
targetstoRender = helpers.preprocess(
targetstoRender) #Put targets to -1; 1
surfaceArray = helpers.generateSurfaceArray(inputRealSize)
inputs_batch = helpers.generateInputRenderings(
rendererInstance,
targetstoRender,
self.batchSize,
nbRenderings,
surfaceArray,
renderingScene,
False,
False,
self.useAmbientLight,
useAugmentationInRenderings=self.useAugmentationInRenderings)
targets_batch = helpers.target_deshape(targetstoRender,
self.nbTargetsToRead)
self.gammaCorrectedInputsBatch = tf.squeeze(inputs_batch, [1])
#tf.summary.image("GammadInputs", helpers.convert(inputs[0, :]), max_outputs=5)
inputs_batch = tf.pow(inputs_batch, 2.2) # correct gamma
if self.logInput:
inputs_batch = helpers.logTensor(inputs_batch)
#Do the random crop, if the crop if fix, crop in the middle
if inputRealSize > self.tileSize:
if self.fixCrop:
xyCropping = (inputRealSize - self.tileSize) // 2
xyCropping = [xyCropping, xyCropping]
else:
xyCropping = tf.random_uniform([1],
0,
inputRealSize -
self.tileSize,
dtype=tf.int32)
inputs_batch = inputs_batch[:, :, xyCropping[0]:xyCropping[0] +
self.tileSize,
xyCropping[0]:xyCropping[0] +
self.tileSize, :]
targets_batch = targets_batch[:, :,
xyCropping[0]:xyCropping[0] +
self.tileSize,
xyCropping[0]:xyCropping[0] +
self.tileSize, :]
#Set shapes
inputs_batch = tf.squeeze(
inputs_batch, [1]
) #Before this the input has a useless dimension in 1 as we have only 1 rendering
inputs_batch.set_shape([None, self.tileSize, self.tileSize, 3])
targets_batch.set_shape(
[None, self.nbTargetsToRead, self.tileSize, self.tileSize, 3])
#Populate the object
self.stepsPerEpoch = int(
math.floor(len(self.pathList) / self.batchSize))
self.inputBatch = inputs_batch
self.targetBatch = targets_batch
self.iterator = iterator
self.pathBatch = paths_batch