classy_vision/meters/accuracy_meter.py [95:140]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if sample_count
            else 0.0
            for k in self._topk
        }

    def get_classy_state(self):
        """Contains the states of the meter."""
        return {
            "name": self.name,
            "top_k": self._topk,
            "total_correct_predictions": self._total_correct_predictions_k.clone(),
            "total_sample_count": self._total_sample_count.clone(),
            "curr_sample_count": self._curr_sample_count.clone(),
            "curr_correct_predictions_k": self._curr_correct_predictions_k.clone(),
        }

    def set_classy_state(self, state):
        assert (
            self.name == state["name"]
        ), "State name {state_name} does not match meter name {obj_name}".format(
            state_name=state["name"], obj_name=self.name
        )
        assert (
            self._topk == state["top_k"]
        ), "top-k of state {state_k} does not match object's top-k {obj_k}".format(
            state_k=state["top_k"], obj_k=self._topk
        )

        # Restore the state -- correct_predictions and sample_count.
        self.reset()
        self._total_correct_predictions_k = state["total_correct_predictions"].clone()
        self._total_sample_count = state["total_sample_count"].clone()
        self._curr_correct_predictions_k = state["curr_correct_predictions_k"].clone()
        self._curr_sample_count = state["curr_sample_count"].clone()

    def update(self, model_output, target, **kwargs):
        """
        args:
            model_output: tensor of shape (B, C) where each value is
                          either logit or class probability.
            target:       tensor of shape (B, C), which is one-hot /
                          multi-label encoded, or tensor of shape (B) /
                          (B, 1), integer encoded
        """
        # Convert target to 0/1 encoding if isn't
        target = maybe_convert_to_one_hot(target, model_output)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



classy_vision/meters/precision_meter.py [96:141]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if sample_count
            else 0.0
            for k in self._topk
        }

    def get_classy_state(self):
        """Contains the states of the meter."""
        return {
            "name": self.name,
            "top_k": self._topk,
            "total_correct_predictions": self._total_correct_predictions_k.clone(),
            "total_sample_count": self._total_sample_count.clone(),
            "curr_sample_count": self._curr_sample_count.clone(),
            "curr_correct_predictions_k": self._curr_correct_predictions_k.clone(),
        }

    def set_classy_state(self, state):
        assert (
            self.name == state["name"]
        ), "State name {state_name} does not match meter name {obj_name}".format(
            state_name=state["name"], obj_name=self.name
        )
        assert (
            self._topk == state["top_k"]
        ), "top-k of state {state_k} does not match object's top-k {obj_k}".format(
            state_k=state["top_k"], obj_k=self._topk
        )

        # Restore the state -- correct_predictions and sample_count.
        self.reset()
        self._total_correct_predictions_k = state["total_correct_predictions"].clone()
        self._total_sample_count = state["total_sample_count"].clone()
        self._curr_correct_predictions_k = state["curr_correct_predictions_k"].clone()
        self._curr_sample_count = state["curr_sample_count"].clone()

    def update(self, model_output, target, **kwargs):
        """
        args:
            model_output: tensor of shape (B, C) where each value is
                          either logit or class probability.
            target:       tensor of shape (B, C), which is one-hot /
                          multi-label encoded, or tensor of shape (B) /
                          (B, 1), integer encoded
        """
        # Convert target to 0/1 encoding if isn't
        target = maybe_convert_to_one_hot(target, model_output)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -