ddqn.py 文件源码

def forward_one_step(self, x, test):
        f = activations[self.activation_function]
        chain = [x]

        # Hidden convolutinal layers
        for i in range(self.n_hidden_layers):
            u = getattr(self, "layer_%i" % i)(chain[-1])
            if self.apply_batchnorm:
                if i == 0 and self.apply_batchnorm_to_input is False:
                    pass
                else:
                    u = getattr(self, "batchnorm_%i" % i)(u, test=test)
            chain.append(f(u))

        if self.projection_type == "fully_connection":
            u = self.projection_layer(chain[-1])
            if self.apply_batchnorm:
                u = self.projection_batchnorm(u, test=test)
            chain.append(f(u))

        elif self.projection_type == "global_average_pooling":
            batch_size = chain[-1].data.shape[0]
            n_maps = chain[-1].data[0].shape[0]
            chain.append(F.average_pooling_2d(chain[-1], self.top_filter_size))
            chain.append(F.reshape(chain[-1], (batch_size, n_maps)))
            u = self.projection_layer(chain[-1])
            if self.apply_batchnorm:
                u = self.projection_batchnorm(u, test=test)
            chain.append(f(u))

        else:
            raise NotImplementedError()

        return chain[-1]