def forward(self, input1, requires_grad=False):
assert (input1.is_contiguous())
# assert(input2.is_contiguous())
# self.input1 = input1.contiguous() # need to use in the backward process, so we need to cache it
fillhole = 1 if requires_grad == False else 0
# if input1.is_cuda:
# self.device = torch.cuda.current_device()
# else:
# self.device = -1
# count = torch.zeros(input1.size(0),1,input1.size(2),input1.size(3)) # for accumulating the homography projections
# output = torch.zeros(input1.size())
if input1.is_cuda:
# output = output.cuda()
# count = count.cuda()
if self.count is None:
#print(input1.type())
if isinstance(input1, torch.cuda.FloatTensor):
self.count = torch.cuda.FloatTensor().resize_(
input1.size(0), 1, input1.size(2),
input1.size(3)).zero_()
self.output = torch.cuda.FloatTensor().resize_(
input1.size()).zero_()
else:
self.count = torch.cuda.HalfTensor().resize_(
input1.size(0), 1, input1.size(2),
input1.size(3)).zero_()
self.output = torch.cuda.HalfTensor().resize_(
input1.size()).zero_()
err = my_lib.FlowProjectionLayer_gpu_forward(
input1, self.count, self.output, fillhole)
else:
output = torch.cuda.FloatTensor(input1.data.size())
err = my_lib.FlowProjectionLayer_cpu_forward(
input1, self.count, output, fillhole)
if err != 0:
print(err)
# output = output/count # to divide the counter
#self.save_for_backward(input1, self.count)
#self.fillhole = fillhole
# self.count = count #to keep this
# print(self.input1[0, 0, :10, :10])
# print(self.count[0, 0, :10, :10])
# print(self.input1[0, 0, -10:, -10:])
# print(self.count[0, 0, -10:, -10:])
# the function returns the output to its caller
return self.output
def forward(ctx, input1, requires_grad):
assert(input1.is_contiguous())
fillhole = 1 if requires_grad == False else 0
if input1.is_cuda :
count = torch.cuda.FloatTensor().resize_(input1.size(0), 1, input1.size(2), input1.size(3)).zero_()
output = torch.cuda.FloatTensor().resize_(input1.size()).zero_()
err = my_lib.FlowProjectionLayer_gpu_forward(input1, count, output, fillhole)
else:
output = torch.cuda.FloatTensor(input1.data.size())
err = my_lib.FlowProjectionLayer_cpu_forward(input1, count, output, fillhole)
if err != 0:
print(err)
ctx.save_for_backward(input1, count)
ctx.fillhole = fillhole
return output