def forward(self, input1):
# 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
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()
err = my_lib.FlowFillholelayer_gpu_forward(input1, output)
else:
# output = torch.cuda.FloatTensor(input1.data.size())
err = my_lib.FlowFillholelayer_cpu_forward(input1, output)
if err != 0:
print(err)
# output = output/count # to divide the counter
# 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 output
def forward(ctx, input1):
output = torch.zeros(input1.size())
if input1.is_cuda :
output = output.cuda()
err = my_lib.FlowFillholelayer_gpu_forward(input1, output)
else:
err = my_lib.FlowFillholelayer_cpu_forward(input1, output)
if err != 0:
print(err)
ctx.save_for_backward(input1.contiguous())
ctx.device = torch.cuda.current_device() if input1.is_cuda else -1
return output