1.py

from multihead_attention import MultiHeadAttention
from encoder import AddNormalization, FeedForward

class DecoderLayer(Layer):
    def __init__(self, h, d_k, d_v, d_model, d_ff, rate, **kwargs):
        super(DecoderLayer, self).__init__(**kwargs)
        self.multihead_attention1 = MultiHeadAttention(h, d_k, d_v, d_model)
        self.dropout1 = Dropout(rate)
        self.add_norm1 = AddNormalization()
        self.multihead_attention2 = MultiHeadAttention(h, d_k, d_v, d_model)
        self.dropout2 = Dropout(rate)
        self.add_norm2 = AddNormalization()
        self.feed_forward = FeedForward(d_ff, d_model)
        self.dropout3 = Dropout(rate)
        self.add_norm3 = AddNormalization()
        ...