This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tensorflow as tf | |
import numpy as np | |
corpus_raw = 'He is the king . The king is royal . She is the royal queen ' | |
# convert to lower case | |
corpus_raw = corpus_raw.lower() | |
words = [] | |
for word in corpus_raw.split(): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch | |
from torch import LongTensor | |
from torch.nn import Embedding, LSTM | |
from torch.autograd import Variable | |
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence | |
## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium'] | |
# | |
# Step 1: Construct Vocabulary | |
# Step 2: Load indexed data (list of instances, where each instance is list of character indices) |