# Codeblock 11
class EncoderTorch(nn.Module):
   def __init__(self):
       super().__init__()
       self.patcher = Patcher()
       self.learnable_embedding = LearnableEmbedding()
      
       #(1)
       encoder_block = nn.TransformerEncoderLayer(d_model=EMBED_DIM,
                                                  nhead=NUM_HEADS,
                                                  dim_feedforward=HIDDEN_DIM,
                                                  dropout=DROP_PROB,
                                                  batch_first=True)
      
       #(2)
       self.encoder_blocks = nn.TransformerEncoder(encoder_layer=encoder_block,
                                                   num_layers=NUM_ENCODER_BLOCKS)
  
   def forward(self, images):
       print(f'images\t\t\t: {images.size()}')
      
       features = self.patcher(images)
       print(f'after patcher\t\t: {features.size()}')
      
       features = features + self.learnable_embedding()
       print(f'after learn embed\t: {features.size()}')
      
       features = self.encoder_blocks(features)  #(3)
       print(f'after encoder blocks\t: {features.size()}')

       return features