imaginaire.third_party.flow_net package


imaginaire.third_party.flow_net.flow_net module

class imaginaire.third_party.flow_net.flow_net.FlowNet(pretrained=True, fp16=False)[source]

Bases: torch.nn.modules.module.Module

compute_flow_and_conf(im1, im2)[source]
forward(input_A, input_B)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.


Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training = None

imaginaire.third_party.flow_net.test_flownet2 module

Module contents