custom_model_save.rb

class PositionalEmbedding(layers.Layer):
    def __init__(self, sequence_length, output_dim, **kwargs):
        super().__init__(**kwargs)
        self.position_embeddings = layers.Embedding(
            input_dim=sequence_length, output_dim=output_dim
        )
        self.sequence_length = sequence_length
        self.output_dim = output_dim

    def call(self, inputs):
        # The inputs are of shape: `(batch_size, frames, num_features)`
        length = tf.shape(inputs)[1]
        positions = tf.range(start=0, limit=length, delta=1)
        embedded_positions = self.position_embeddings(positions)
        return inputs + embedded_positions

    def compute_mask(self, inputs, mask=None):
        mask = tf.reduce_any(tf.cast(inputs, "bool"), axis=-1)
        return mask
        
class TransformerEncoder(layers.Layer):
    def __init__(self, embed_dim, dense_dim, num_heads, **kwargs):
        super().__init__(**kwargs)
        self.embed_dim = embed_dim
        self.dense_dim = dense_dim
        self.num_heads = num_heads
        self.attention = layers.MultiHeadAttention(
            num_heads=num_heads, key_dim=embed_dim, dropout=0.3
        )
        self.dense_proj = keras.Sequential(
            [layers.Dense(dense_dim, activation=tf.nn.gelu), layers.Dense(embed_dim),]
        )
        self.layernorm_1 = layers.LayerNormalization()
        self.layernorm_2 = layers.LayerNormalization()

    def call(self, inputs, mask=None):
        if mask is not None:
            mask = mask[:, tf.newaxis, :]

        attention_output = self.attention(inputs, inputs, attention_mask=mask)
        proj_input = self.layernorm_1(inputs + attention_output)
        proj_output = self.dense_proj(proj_input)
        return self.layernorm_2(proj_input + proj_output)
          
lr_schedule = keras.optimizers.schedules.ExponentialDecay(
    initial_learning_rate=1e-2,
    decay_steps=10000,
    decay_rate=0.001)
optimizer = keras.optimizers.SGD(learning_rate=lr_schedule)
          
def get_compiled_model():
    sequence_length = 70
    embed_dim = 1280
    dense_dim = 32
    num_heads = 3
    classes = len(label_processor)

    inputs = keras.Input(shape=(None, None))
    x = PositionalEmbedding(
        sequence_length, embed_dim, name="frame_position_embedding"
    )(inputs)
    x = TransformerEncoder(embed_dim, dense_dim, num_heads, name="transformer_layer")(x)
    x = layers.GlobalMaxPooling1D()(x)
    x = layers.Dropout(0.5)(x)
    outputs = layers.Dense(classes, activation="softmax")(x)
    model = keras.Model(inputs, outputs)
    optimizer = keras.optimizers.SGD(learning_rate=lr_schedule)
    model.compile(
        optimizer=optimizer, loss="sparse_categorical_crossentropy", metrics=["accuracy"]
    )
    return model
seq_model=get_compiled_model()
seq_model.load_weights('video_classifierx (1)')
seq_model.save('activity_classifier.h5')