INNER CODE UNIT · Python
encoder_dim
graviraja/100-Days-of-NLP · applications/generation/image_captioning/latex_app/app.py:96
encoder_dim = encoded_image.size(-1)
encoder_out = encoded_image.view(batch_size, -1, encoder_dim)
# encoder_out => [1, 16, 512]
num_pixels = encoder_out.size(1)
hidden, cell = model.init_hidden_state(encoder_out)
# hidden, cell => [1, decoder_dim]
hidden = hidden.unsqueeze(0)
cell = cell.unsqueeze(0)
# hidden, cell => [1, 1, decoder_dim]
dec_inp = torch.LongTensor([vocab('<s>')]).to(device)
sampled_ids = []
for t in range(1, max_len):
output, hidden, cell, _ = model.decoder(dec_inp.unsqueeze(1), hidden, cell, encoder_out)