generate.py

###############################################################################
# Language Modeling on Penn Tree Bank
#
# This file generates new sentences sampled from the language model
#
###############################################################################

import argparse
import numpy as np
import torch
from torch.autograd import Variable

import data

parser = argparse.ArgumentParser(description='PyTorch Wikitext-2 Language Model')

# Model parameters.
parser.add_argument('--data', type=str, default='./data/wikitext-2',
                    help='location of the data corpus')
parser.add_argument('--checkpoint', type=str, default='./model.pt',
                    help='model checkpoint to use')
parser.add_argument('--outf', type=str, default='generated.txt',
                    help='output file for generated text')
parser.add_argument('--words', type=int, default='1000',
                    help='number of words to generate')
parser.add_argument('--seed', type=int, default=1111,
                    help='random seed')
parser.add_argument('--cuda', action='store_true',
                    help='use CUDA')
parser.add_argument('--temperature', type=float, default=1.0,
                    help='temperature - higher will increase diversity')
parser.add_argument('--log-interval', type=int, default=100,
                    help='reporting interval')
args = parser.parse_args()

# Set the random seed manually for reproducibility.
torch.manual_seed(args.seed)
if torch.cuda.is_available():
    if not args.cuda:
        print("WARNING: You have a CUDA device, so you should probably run with --cuda")

device = torch.device("cuda" if args.cuda else "cpu")

if args.temperature < 1e-3:
    parser.error("--temperature has to be greater or equal 1e-3")

with open(args.checkpoint, 'rb') as f:
    model = torch.load(f).to(device)
model.eval()

corpus = data.Corpus(args.data)
ntokens = len(corpus.dictionary)
hidden = model.init_hidden(1)
input = torch.randint(ntokens, (1, 1), dtype=torch.long).to(device)


f = open('../../rnng-model/input_islandswh.raw', 'r')
lines = f.readlines()
f.close()
sents = [line.strip().split() for line in lines]


with open(args.outf, 'w') as outf:
    with torch.no_grad():  # no tracking history
        for i in range(args.words):
            output, hidden = model(input, hidden)
            word_weights = output.squeeze().div(args.temperature).exp().cpu()
            word_idx = torch.multinomial(word_weights, 1)[0]
            input.fill_(word_idx)
            word = corpus.dictionary.idx2word[word_idx]

            outf.write(word + ('\n' if i % 20 == 19 else ' '))

            if i % args.log_interval == 0:
                print('| Generated {}/{} words'.format(i, args.words))

        #sents = [['Not', 'all', 'those', 'who', 'wrote', 'oppose', 'the', 'changes', '.']]
        for sent in sents:
            hidden = model.init_hidden(1)
            input = torch.tensor([[corpus.dictionary.word2idx[sent[0]]]],dtype=torch.long).to(device)
            print(sent[0]+'\t'+'0.0')
            for i, w in enumerate(sent[1:]):
                output, hidden = model(input, hidden)
                word_weights = output.squeeze().div(args.temperature).exp().cpu()
                word_idx = corpus.dictionary.word2idx[w]
                #print(type(word_weights), len(torch.Tensor.numpy(word_weights)))
                logits = torch.Tensor.numpy(word_weights)
                logits_total = np.sum(logits)
                print(w+'\t'+str(-np.log(logits[word_idx]/logits_total)))
                surprisal = -np.log(word_weights[word_idx])
                #print(w, surprisal)
                input.fill_(word_idx)
            print('<eos>\t0.0')