ss_baselines/av_nav/ppo/ppo_trainer.py [391:454]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                if update % self.config.CHECKPOINT_INTERVAL == 0:
                    self.save_checkpoint(f"ckpt.{count_checkpoints}.pth")
                    count_checkpoints += 1

            self.envs.close()

    def _eval_checkpoint(
        self,
        checkpoint_path: str,
        writer: TensorboardWriter,
        checkpoint_index: int = 0
    ) -> Dict:
        r"""Evaluates a single checkpoint.

        Args:
            checkpoint_path: path of checkpoint
            writer: tensorboard writer object for logging to tensorboard
            checkpoint_index: index of cur checkpoint for logging

        Returns:
            None
        """
        random.seed(self.config.SEED)
        np.random.seed(self.config.SEED)
        torch.manual_seed(self.config.SEED)
            
        # Map location CPU is almost always better than mapping to a CUDA device.
        ckpt_dict = self.load_checkpoint(checkpoint_path, map_location="cpu")

        if self.config.EVAL.USE_CKPT_CONFIG:
            config = self._setup_eval_config(ckpt_dict["config"])
        else:
            config = self.config.clone()

        ppo_cfg = config.RL.PPO

        config.defrost()
        config.TASK_CONFIG.DATASET.SPLIT = config.EVAL.SPLIT
        if self.config.DISPLAY_RESOLUTION != config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.WIDTH:
            model_resolution = config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.WIDTH
            config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.WIDTH = config.TASK_CONFIG.SIMULATOR.RGB_SENSOR.HEIGHT = \
                config.TASK_CONFIG.SIMULATOR.RGB_SENSOR.WIDTH = config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.HEIGHT = \
                self.config.DISPLAY_RESOLUTION
        else:
            model_resolution = self.config.DISPLAY_RESOLUTION
        config.freeze()

        if len(self.config.VIDEO_OPTION) > 0:
            config.defrost()
            config.TASK_CONFIG.TASK.MEASUREMENTS.append("TOP_DOWN_MAP")
            config.TASK_CONFIG.TASK.MEASUREMENTS.append("COLLISIONS")
            config.freeze()
        elif "top_down_map" in self.config.VISUALIZATION_OPTION:
            config.defrost()
            config.TASK_CONFIG.TASK.MEASUREMENTS.append("TOP_DOWN_MAP")
            config.freeze()

        logger.info(f"env config: {config}")
        self.envs = construct_envs(
            config, get_env_class(config.ENV_NAME)
        )
        if self.config.DISPLAY_RESOLUTION != model_resolution:
            observation_space = self.envs.observation_spaces[0]
            observation_space.spaces['depth'].shape = (model_resolution, model_resolution, 1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



ss_baselines/savi/ppo/ppo_trainer.py [654:717]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                if update % self.config.CHECKPOINT_INTERVAL == 0:
                    self.save_checkpoint(f"ckpt.{count_checkpoints}.pth")
                    count_checkpoints += 1

            self.envs.close()

    def _eval_checkpoint(
        self,
        checkpoint_path: str,
        writer: TensorboardWriter,
        checkpoint_index: int = 0
    ) -> Dict:
        r"""Evaluates a single checkpoint.

        Args:
            checkpoint_path: path of checkpoint
            writer: tensorboard writer object for logging to tensorboard
            checkpoint_index: index of cur checkpoint for logging

        Returns:
            None
        """
        random.seed(self.config.SEED)
        np.random.seed(self.config.SEED)
        torch.manual_seed(self.config.SEED)
            
        # Map location CPU is almost always better than mapping to a CUDA device.
        ckpt_dict = self.load_checkpoint(checkpoint_path, map_location="cpu")

        if self.config.EVAL.USE_CKPT_CONFIG:
            config = self._setup_eval_config(ckpt_dict["config"])
        else:
            config = self.config.clone()

        ppo_cfg = config.RL.PPO

        config.defrost()
        config.TASK_CONFIG.DATASET.SPLIT = config.EVAL.SPLIT
        if self.config.DISPLAY_RESOLUTION != config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.WIDTH:
            model_resolution = config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.WIDTH
            config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.WIDTH = config.TASK_CONFIG.SIMULATOR.RGB_SENSOR.HEIGHT = \
                config.TASK_CONFIG.SIMULATOR.RGB_SENSOR.WIDTH = config.TASK_CONFIG.SIMULATOR.DEPTH_SENSOR.HEIGHT = \
                self.config.DISPLAY_RESOLUTION
        else:
            model_resolution = self.config.DISPLAY_RESOLUTION
        config.freeze()

        if len(self.config.VIDEO_OPTION) > 0:
            config.defrost()
            config.TASK_CONFIG.TASK.MEASUREMENTS.append("TOP_DOWN_MAP")
            config.TASK_CONFIG.TASK.MEASUREMENTS.append("COLLISIONS")
            config.freeze()
        elif "top_down_map" in self.config.VISUALIZATION_OPTION:
            config.defrost()
            config.TASK_CONFIG.TASK.MEASUREMENTS.append("TOP_DOWN_MAP")
            config.freeze()

        logger.info(f"env config: {config}")
        self.envs = construct_envs(
            config, get_env_class(config.ENV_NAME)
        )
        if self.config.DISPLAY_RESOLUTION != model_resolution:
            observation_space = self.envs.observation_spaces[0]
            observation_space.spaces['depth'].shape = (model_resolution, model_resolution, 1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -