def __init__(self, num_pixels, layers, H_decision, imageSize):
super(PropagationOnly_SharedPixel, self).__init__()
weightMask, diagMask, edgeMask, cornerMask = generateFixedWeightMask_PredPrey(
imageSize)
self.iteratedLayer_Pred = RangePropgation_SharedPixel(
num_pixels, num_pixels, layers, weightMask, diagMask, edgeMask,
cornerMask)
def __init__(self, num_pixels, layers, H_decision, imageSize):
super(FixedAll_PredPrey, self).__init__()
weightMask, diagMask, edgeMask, cornerMask = generateFixedWeightMask_PredPrey(
imageSize)
self.iteratedLayer = RecurrentDecision_FixedAll(
num_pixels, num_pixels, layers, weightMask, diagMask, edgeMask,
cornerMask)
def __init__(self, num_pixels, layers, H_decision, imageSize):
super(Fixed_PredPrey, self).__init__()
weightMask, diagMask, edgeMask, cornerMask = generateFixedWeightMask_PredPrey(
imageSize)
self.iteratedLayer = FixedPropagationDecision(num_pixels, num_pixels,
layers, weightMask,
diagMask, edgeMask,
cornerMask)
def __init__(self, num_pixels, layers, H_decision, imageSize):
super(RecurrentSharedPixel_PredPrey, self).__init__()
weightMask, diagMask, edgeMask, cornerMask = generateFixedWeightMask_PredPrey(
imageSize)
self.iteratedLayer_Pred = RepeatedLayersSharedPixel(
num_pixels, num_pixels, layers, weightMask, diagMask, edgeMask,
cornerMask)
self.tanh = nn.Tanh()
cmap2._init() # create the _lut array, with rgba values
cmap3._init()
# create your alpha array and fill the colormap with them.
# here it is progressive, but you can create whathever you want
alphas = np.linspace(0, 0.8, cmap2.N + 3)
cmap2._lut[:, -1] = alphas
cmap3._lut[:, -1] = alphas
# General parameters that would get set in other code
image_size = 15
N = image_size
num_nodes = image_size**2
weightMask, diagMask, edgeMask, cornerMask = generateFixedWeightMask_PredPrey(
image_size)
centerMask = ~(edgeMask + cornerMask)
dtype = torch.FloatTensor
testDict = generateSamples(image_size, 2, 10)
for i in range(3):
modelBlock_State = torch.load(model_path + model_name[i],
map_location=torch.device('cpu'))
modelBlock = loadStateDict(modelBlock_State)
layers = layers_list[i]