def forward(
ctx, input1, input2, pad_size=3, kernel_size=3, max_displacement=20, stride1=1, stride2=2, corr_multiply=1
):
ctx.save_for_backward(input1, input2)
ctx.pad_size = pad_size
ctx.kernel_size = kernel_size
ctx.max_displacement = max_displacement
ctx.stride1 = stride1
ctx.stride2 = stride2
ctx.corr_multiply = corr_multiply
with torch.cuda.device_of(input1):
rbot1 = input1.new()
rbot2 = input2.new()
output = input1.new()
correlation_cuda.forward(
input1,
input2,
rbot1,
rbot2,
output,
ctx.pad_size,
ctx.kernel_size,
ctx.max_displacement,
ctx.stride1,
ctx.stride2,
ctx.corr_multiply,
)
return output
def forward(self, input1, input2):
self.save_for_backward(input1, input2)
with torch.cuda.device_of(input1):
rbot1 = input1.new()
rbot2 = input2.new()
output = input1.new()
correlation_cuda.forward(input1, input2, rbot1, rbot2, output,
self.pad_size, self.kernel_size, self.max_displacement,self.stride1, self.stride2, self.corr_multiply)
return output
def forward(ctx, input1, input2, pad, kernel, max_d, stride1, stride2, corr_m):
ctx.save_for_backward(input1, input2)
ctx.arg = pad, kernel, max_d, stride1, stride2, corr_m
rbot1 = torch.empty_like(input1)
rbot2 = torch.empty_like(input2)
output = torch.empty_like(input1)
correlation_cuda.forward(input1, input2, rbot1, rbot2, output,
pad, kernel, max_d, stride1, stride2, corr_m)
return output
def forward(self, input1, input2):
self.save_for_backward(input1, input2)
rbot1 = torch.empty_like(input1)
rbot2 = torch.empty_like(input2)
output = torch.empty_like(input1)
correlation_cuda.forward(input1, input2, rbot1, rbot2, output,
self.pad_size, self.kernel_size,
self.max_displacement, self.stride1,
self.stride2, self.corr_multiply)
return output
def forward(ctx, input1, input2, params):
ctx.save_for_backward(input1, input2)
with torch.cuda.device_of(input1):
rbot1 = input1.new()
rbot2 = input2.new()
output = input1.new()
correlation_cuda.forward(
input1, input2, rbot1, rbot2,
output,
params.pad_size, params.kernel_size, params.max_displacement, params.stride1, params.stride2,
params.corr_multiply
)
return output
def forward(self, input1, input2):
self.save_for_backward(input1, input2)
kH, kW = self.kernel_size
patchH, patchW = self.patch_size
padH, padW = self.padding
dilation_patchH, dilation_patchW = self.dilation_patch
dH, dW = self.stride
output = correlation_cuda.forward(
input1,
input2,
kH,
kW,
patchH,
patchW,
padH,
padW,
dilation_patchH,
dilation_patchW,
dH,
dW,
)
return output
def forward(ctx, input1, input2, pad_size, kernel_size, max_displacement,
stride1, stride2, corr_multiply):
ctx.save_for_backward(input1, input2)
ctx.pad_size, ctx.kernel_size, ctx.max_displacement, ctx.stride1, ctx.stride2, ctx.corr_multiply =\
pad_size, kernel_size, max_displacement, stride1, stride2, corr_multiply
with torch.cuda.device_of(input1):
rbot1 = input1.new()
rbot2 = input2.new()
output = input1.new()
#correlation_cuda.forward(input1, input2, rbot1, rbot2, output,
# self.pad_size, self.kernel_size, self.max_displacement,self.stride1, self.stride2, self.corr_multiply)
correlation_cuda.forward(input1, input2, rbot1, rbot2, output,
ctx.pad_size, ctx.kernel_size,
ctx.max_displacement, ctx.stride1,
ctx.stride2, ctx.corr_multiply)
return output
def forward(ctx, input1, input2, param_dict):
ctx.save_for_backward(input1, input2)
ctx.pad_size = param_dict["pad_size"]
ctx.kernel_size = param_dict["kernel_size"]
ctx.max_disp = param_dict["max_disp"]
ctx.stride1 = param_dict["stride1"]
ctx.stride2 = param_dict["stride2"]
ctx.corr_multiply = param_dict["corr_multiply"]
with torch.cuda.device_of(input1):
rbot1 = input1.new()
rbot2 = input2.new()
output = input1.new()
correlation_cuda.forward(input1, input2, rbot1, rbot2, output,
ctx.pad_size, ctx.kernel_size,
ctx.max_disp, ctx.stride1, ctx.stride2,
ctx.corr_multiply)
return output
