def main():
model_config = config.get_model_config()
num_input_words = model_config['dim_lang']
world_state_size = model_config['dim_world']
num_output_actions = model_config['dim_action']
hidden_size = model_config['hidden_size']
learning_rate = model_config['learning_rate']
encoder = models.EncoderRNN(num_input_words, hidden_size, bidirectionality=True)
attn_decoder = models.AttnDecoderRNN(hidden_size, world_state_size, num_output_actions)
trainIters(encoder, attn_decoder, 1, learning_rate)
id_process = os.getpid()
time_current = datetime.datetime.now().isoformat()
tag_model = '_PID=' + str(id_process) + '_TIME=' + time_current
path_track = './tracks/track' + tag_model + '/'
command_mkdir = 'mkdir -p ' + os.path.abspath(
path_track
)
os.system(command_mkdir)
#
ENCODER_PATH = path_track + 'encoder.pkl'
DECODER_PATH = path_track + 'decoder.pkl'
torch.save(encoder, ENCODER_PATH)
torch.save(attn_decoder, DECODER_PATH)
def main():
model_config = config.get_model_config()
num_input_words = model_config['dim_lang']
world_state_size = model_config['dim_world']
num_output_actions = model_config['dim_action']
hidden_size = model_config['hidden_size']
learning_rate = model_config['learning_rate']
encoder = models.EncoderRNN(num_input_words, hidden_size, bidirectionality=True)
attn_decoder = models.AttnDecoderRNN(hidden_size, world_state_size, num_output_actions)
trainIters(encoder, attn_decoder, 3, learning_rate)
if __name__ == '__main__':
#hyper-parameters
# #other parameters can be found in configs.py, but better to keep default
use_model = False #True:use the trained model, else training from scratch
hidden_size = 256 #rnn's hidden_size
in_embed_dim = 256 #input language word embedding dimension
out_embed_dim = 256 #output language word embedding dimension
lr = 0.01
n_iters = 80000
print_every = 1000
plot_every = 100
encoder1 = models.EncoderRNN(input_lang.n_words, hidden_size, in_embed_dim).to(device)
attn_decoder1 = models.AttnDecoderRNN(hidden_size, output_lang.n_words, out_embed_dim, dropout_p=0.1).to(device)
if use_model:
encoder1.load_state_dict(torch.load('data/encoder_25.pt'))
attn_decoder1.load_state_dict(torch.load('data/attn_decoder_25.pt'))
else:
trainIters(pairs, input_lang, output_lang, encoder1, attn_decoder1, n_iters=n_iters, print_every=print_every, plot_every=plot_every, learning_rate=lr)
evaluateRandomly(pairs, input_lang, output_lang, encoder1, attn_decoder1)
evaluateInput(input_lang, output_lang, encoder1, attn_decoder1)