mmf/models/pythia.py [216:267]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def process_feature_embedding(
        self, attr, sample_list, text_embedding_total, extra=None, batch_size_t=None
    ):
        if extra is None:
            extra = []
        feature_embeddings = []
        feature_attentions = []
        features = []
        batch_size_t = (
            sample_list.get_batch_size() if batch_size_t is None else batch_size_t
        )

        # Convert list of keys to the actual values
        extra = sample_list.get_fields(extra)

        feature_idx = 0

        # Get all of the features, which are in the form, "image_feature_0"
        # "image_feature_1" ...
        while True:
            feature = getattr(sample_list, f"{attr}_feature_{feature_idx:d}", None)
            if feature is None:
                break
            feature_idx += 1
            feature = feature[:batch_size_t]
            features.append(feature)

        feature_encoders = getattr(self, attr + "_feature_encoders")
        # Each feature should have a separate image feature encoders
        assert len(features) == len(feature_encoders), (
            "Number of feature encoders, {} are not equal "
            "to number of features, {}.".format(len(feature_encoders), len(features))
        )

        # Now, iterate to get final attended image features
        for i, feature in enumerate(features):
            # Get info related to the current feature. info is generally
            # in key of format "image_info_0" for 0th feature
            feature_info = getattr(sample_list, f"{attr}_info_{i:d}", {})
            # For Pythia, we need max_features to mask attention
            feature_dim = getattr(feature_info, "max_features", None)
            if feature_dim is not None:
                feature_dim = feature_dim[:batch_size_t]

            # Attribute in which encoders are saved, for "image" it
            # will be "image_feature_encoders", other example is
            # "context_feature_encoders"
            encoders_attr = attr + "_feature_encoders"
            feature_encoder = getattr(self, encoders_attr)[i]

            # Encode the features
            encoded_feature = feature_encoder(feature)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



mmf/models/pythia.py [437:488]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def process_feature_embedding(
        self, attr, sample_list, text_embedding_total, extra=None, batch_size_t=None
    ):
        if extra is None:
            extra = []
        feature_embeddings = []
        feature_attentions = []
        features = []
        batch_size_t = (
            sample_list.get_batch_size() if batch_size_t is None else batch_size_t
        )

        # Convert list of keys to the actual values
        extra = sample_list.get_fields(extra)

        feature_idx = 0

        # Get all of the features, which are in the form, "image_feature_0"
        # "image_feature_1" ...
        while True:
            feature = getattr(sample_list, f"{attr}_feature_{feature_idx:d}", None)
            if feature is None:
                break
            feature_idx += 1
            feature = feature[:batch_size_t]
            features.append(feature)

        feature_encoders = getattr(self, attr + "_feature_encoders")
        # Each feature should have a separate image feature encoders
        assert len(features) == len(feature_encoders), (
            "Number of feature encoders, {} are not equal "
            "to number of features, {}.".format(len(feature_encoders), len(features))
        )

        # Now, iterate to get final attended image features
        for i, feature in enumerate(features):
            # Get info related to the current feature. info is generally
            # in key of format "image_info_0" for 0th feature
            feature_info = getattr(sample_list, f"{attr}_info_{i:d}", {})
            # For Pythia, we need max_features to mask attention
            feature_dim = getattr(feature_info, "max_features", None)
            if feature_dim is not None:
                feature_dim = feature_dim[:batch_size_t]

            # Attribute in which encoders are saved, for "image" it
            # will be "image_feature_encoders", other example is
            # "context_feature_encoders"
            encoders_attr = attr + "_feature_encoders"
            feature_encoder = getattr(self, encoders_attr)[i]

            # Encode the features
            encoded_feature = feature_encoder(feature)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -