future_predictor_agent_basic.py 文件源码

def make_net(self, input_images, input_measurements, input_actions, input_objectives, reuse=False):
        if reuse:
            tf.get_variable_scope().reuse_variables()

        self.fc_joint_params['out_dims'][-1] = len(self.net_discrete_actions) * self.target_dim
        p_img_conv = my_ops.conv_encoder(input_images, self.conv_params, 'p_img_conv', msra_coeff=0.9)
        p_img_fc = my_ops.fc_net(my_ops.flatten(p_img_conv), self.fc_img_params, 'p_img_fc', msra_coeff=0.9)
        p_meas_fc = my_ops.fc_net(input_measurements, self.fc_meas_params, 'p_meas_fc', msra_coeff=0.9)
        if isinstance(self.fc_obj_params, np.ndarray):
            p_obj_fc = my_ops.fc_net(input_objectives, self.fc_obj_params, 'p_obj_fc', msra_coeff=0.9)
            p_concat_fc = tf.concat([p_img_fc,p_meas_fc,p_obj_fc], 1)
        else:
            p_concat_fc = tf.concat([p_img_fc,p_meas_fc], 1)
            if self.random_objective_coeffs:
                raise Exception('Need fc_obj_params with randomized objectives')

        p_joint_fc = my_ops.fc_net(p_concat_fc, self.fc_joint_params, 'p_joint_fc', last_linear=True, msra_coeff=0.9)
        pred_all = tf.reshape(p_joint_fc, [-1, len(self.net_discrete_actions), self.target_dim])
        pred_relevant = tf.boolean_mask(pred_all, tf.cast(input_actions, tf.bool))

        return pred_all, pred_relevant