def run(model, voc):
# Set dropout layers to eval mode
model.eval()
# Initialize search module
if config.BEAM_SEARCH_ON:
searcher = BeamSearchDecoder(model)
else:
searcher = GreedySearchDecoder(model)
# Begin chatting (uncomment and run the following line to begin)
evaluateInput(searcher, voc)
def run(args):
# Initialize word embeddings
embedding = nn.Embedding(voc.num_words, hidden_size)
# Initialize encoder & decoder models
encoder = EncoderRNN(hidden_size, embedding, encoder_n_layers, dropout)
decoder = LuongAttnDecoderRNN(attn_model, embedding, hidden_size,
voc.num_words, decoder_n_layers, dropout)
# Use appropriate device
encoder = encoder.to(device)
decoder = decoder.to(device)
# Initialize optimizers
encoder_optimizer = optim.Adam(encoder.parameters(), lr=learning_rate)
decoder_optimizer = optim.Adam(decoder.parameters(),
lr=learning_rate * decoder_learning_ratio)
if (args.train):
loadFilename = None
print('Building encoder and decoder ...')
print('Building optimizers ...')
print('Models built and ready to go!')
# Ensure dropout layers are in train mode
encoder.train()
decoder.train()
# Run training iterations
print("Starting Training!")
trainIters(model_name, voc, pairs, encoder, decoder, encoder_optimizer,
decoder_optimizer, embedding, encoder_n_layers,
decoder_n_layers, save_dir, n_iteration, batch_size,
print_every, save_every, clip, corpus_name, loadFilename,
args.name)
if (args.evaluate):
# Set checkpoint to load from; set to None if starting from scratch
loadFilename = os.path.join(
save_dir, model_name, corpus_name,
'{}-{}_{}_{}'.format(encoder_n_layers, decoder_n_layers,
hidden_size, args.name),
'{}_checkpoint.tar'.format(checkpoint_iter))
# Load model if a loadFilename is provided
if loadFilename:
# If loading on same machine the model was trained on
# checkpoint = torch.load(loadFilename)
# If loading a model trained on GPU to CPU
checkpoint = torch.load(loadFilename,
map_location=torch.device('cpu'))
encoder_sd = checkpoint['en']
decoder_sd = checkpoint['de']
encoder_optimizer_sd = checkpoint['en_opt']
decoder_optimizer_sd = checkpoint['de_opt']
embedding_sd = checkpoint['embedding']
voc.__dict__ = checkpoint['voc_dict']
if loadFilename:
embedding.load_state_dict(embedding_sd)
encoder.load_state_dict(encoder_sd)
decoder.load_state_dict(decoder_sd)
encoder_optimizer.load_state_dict(encoder_optimizer_sd)
decoder_optimizer.load_state_dict(decoder_optimizer_sd)
# Set dropout layers to eval mode
encoder.eval()
decoder.eval()
# Begin chatting (uncomment and run the following line to begin)
evaluateInput(encoder, decoder, voc, args.beam, args.name)
def evaluate_mode(word_index_dict):
encoder, decoder = model_manager.get_models(
word_index_dict) # 学習済みモデルデータのロード。
searcher = network_model.GreedySearchDecoder(encoder, decoder) # 返事をするモデル。
evaluate.evaluateInput(encoder, decoder, searcher,
word_index_dict) # 入力受付開始。
encoder.train()
decoder.train()
# Initialize optimizers
print('Building optimizers ...')
encoder_optimizer = optim.Adam(encoder.parameters(), lr=learning_rate)
decoder_optimizer = optim.Adam(decoder.parameters(),
lr=learning_rate * decoder_learning_ratio)
if loadFilename:
encoder_optimizer.load_state_dict(encoder_optimizer_sd)
decoder_optimizer.load_state_dict(decoder_optimizer_sd)
# Run training iterations
print("Starting Training!")
trainIters(model_name, voc, pairs, encoder, decoder, encoder_optimizer,
decoder_optimizer, embedding, encoder_n_layers, decoder_n_layers,
save_dir, n_iteration, batch_size, print_every, save_every, clip,
corpus_name, loadFilename)
# Set dropout layers to eval mode
encoder.eval()
decoder.eval()
# Initialize search module
searcher = GreedySearchDecoder(encoder, decoder, device)
# Begin chatting (uncomment and run the following line to begin)
evaluateInput(searcher, voc)
###################################################################### # Run Evaluation # ~~~~~~~~~~~~~~ # # To chat with your model, run the following block. # # Set dropout layers to eval mode encoder.eval() decoder.eval() # Initialize search module searcher = GreedySearchDecoder(encoder, decoder) # Begin chatting (uncomment and run the following line to begin) evaluateInput(encoder, decoder, searcher, voc, MAX_LENGTH) ###################################################################### # Conclusion # ---------- # # That’s all for this one, folks. Congratulations, you now know the # fundamentals to building a generative chatbot model! If you’re # interested, you can try tailoring the chatbot’s behavior by tweaking the # model and training parameters and customizing the data that you train # the model on. # # Check out the other tutorials for more cool deep learning applications # in PyTorch! #