def forward(ctx, input1, input2):
assert(input1.is_contiguous())
assert(input2.is_contiguous())
if input1.is_cuda :
# output = output.cuda()
output = torch.cuda.FloatTensor().resize_(input1.size()).zero_()
my_lib.InterpolationLayer_gpu_forward(input1, input2, output)
else:
output = torch.cuda.FloatTensor(input1.data.size())
my_lib.InterpolationLayer_cpu_forward(input1, input2, output)
ctx.save_for_backward(input1, input2)
return output
def forward(ctx, input1, input2):
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
# self.input2 = input2.contiguous() # TODO: Note that this is simply a shallow copy?
# if input1.is_cuda:
# self.device = torch.cuda.current_device()
# else:
# self.device = -1
# output = torch.zeros(input1.size())
if input1.is_cuda:
# output = output.cuda()
output = torch.cuda.FloatTensor().resize_(input1.size()).zero_()
my_lib.InterpolationLayer_gpu_forward(input1, input2, output)
else:
output = torch.cuda.FloatTensor(input1.data.size())
my_lib.InterpolationLayer_cpu_forward(input1, input2, output)
ctx.save_for_backward(input1, input2)
# the function returns the output to its caller
return output