michelkana

decoded_imgs_test_32, x_test_32 = plot_mnist_predict(x_test, 
                                                     x_test_noisy, 
                                                     autoencoder_32, 
                                                     y_test, 
                                                     labels=[3, 6, 8])

michelkana

from keras import models
from keras import layers
from keras.applications import VGG16

conv_base = VGG16(weights='imagenet',
                  include_top=False,
                  input_shape=(150, 150, 3))
                  
train_features = conv_base.predict(inputs)

michelkana

import tensorflow as tf

# defining the graph
a = tf.constant([5,3], name="input_a")
b = tf.reduce_prod(a, name="prod_b")
c = tf.reduce_sum(a, name="sum_c")
d = tf.add(b,c, name="add_d")

# running the graph
sess = tf.Session()

michelkana

import numpy as np
from keras.datasets import imdb
from keras.preprocessing import sequence

# number of distinct words
vocabulary_size = 10000

# number of words per review
max_review_length = 500

michelkana

# A dictionary mapping words to an integer index
word_index = imdb.get_word_index()
# The first indices are reserved
word_index = {k:(v+3) for k,v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2  # unknown
word_index["<UNUSED>"] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
# display review

michelkana

from keras.models import Sequential
from keras.layers import Dense, LSTM, SimpleRNN, Flatten
from keras.layers.embeddings import Embedding
from keras.layers.convolutional import Conv1D, MaxPooling1D
import pandas as pd

# Fully connected neural network
model_ffn = Sequential()
model_ffn.add(Dense(250, activation='relu',input_dim=max_review_length))
model_ffn.add(Dense(1, activation='sigmoid'))

michelkana

def movie_sentiment(reviews, 
                    models=[model_ffn, model_ffne, model_cnn, model_rnn, model_cnn_rnn],
                    titles=['FFN', 'FFNE', 'CNN', 'RNN', 'CNN+RNN']):
    df = pd.DataFrame(columns=['review']+titles)
    i =0
    for review in reviews:
        words = set(text_to_word_sequence(review))
        words = [word_index[w] for w in words]
        words = sequence.pad_sequences([words], maxlen=max_review_length)
        df.loc[i] = [review] + titles

michelkana

import pandas as pd
import numpy as np

# load English-Yemba dictionary as CSV file
df = pd.read_csv('https://gist.githubusercontent.com/michelkana/37ccb5c68b3c72148c2b490c917b13aa/raw/9badee0c1811fa03e8b981763e51ddc8ee56513b/english_yemba_dictionary.csv')

# display few words pairs
df.sample(frac=.1).head(15)

michelkana

max_word_len = df.yb.str.len().max()
max_word_len_utf8 = df.yb_utf8.str.len().max()
nb_labels = len(df.word_type.unique())
nb_words = df.shape[0]
print("Number of words: ", nb_words)
print("Number of labels: ", nb_labels)
print("Max word length: {} characters and {} bytes".format(max_word_len, max_word_len_utf8))

michelkana

# Create letter to token dictionary
chars = sorted(list(set(' '.join(df.yb))))
letter2idx = dict((c, i+1) for i, c in enumerate(chars))
# Create token to letter dictionary
idx2letter = dict((i, c) for c, i in letter2idx.items())
vocabulary_size = len(letter2idx)+1
print("Vocabulary size: ", vocabulary_size)