def test_training_performance(self):
n = NoOutputLstm(100, 80)
training_data = []
for _ in range(30):
xs = np.asarray([np.random.uniform(size=100),
np.random.uniform(size=100),
np.random.uniform(size=100),
np.random.uniform(size=100),
np.random.uniform(size=100),
np.random.uniform(size=100),
np.random.uniform(size=100),
np.random.uniform(size=100)])
h0 = np.random.uniform(size=80)
t = np.random.uniform(size=80)
training_data.append((xs, h0, t))
epochs = 100
start = time.time()
for _ in range(epochs):
for xs, h0, t in training_data:
intermediate_results = {}
h_last = n.forward_prop(xs, h0, intermediate_results)
n.back_prop(ce_err_prime(h_last, t), intermediate_results)
n.train(0.1, intermediate_results)
end = time.time()
time_taken = end - start
print(str(epochs) + " training epochs took " + str(time_taken) + " seconds")
def test_learn_word_vectors_from_char_vector_sequence(self):
text = "please learn how to infer word vectors from sequences of character vectors"
index_to_word = list(set(text.split()))
index_to_char = list(set(text))
word_to_index = {
word: index
for index, word in enumerate(index_to_word)
}
char_to_index = {
word: index
for index, word in enumerate(index_to_char)
}
def to_char_vector_sequence(word):
sequence = []
for char in word:
vector = np.ones(len(char_to_index)) * -1
vector[char_to_index[char]] = 1
sequence.append(vector)
sequence.append(np.zeros(len(char_to_index)))
return np.asarray(sequence)
def to_word_vector(word):
vector = np.ones(len(word_to_index)) * -1
vector[word_to_index[word]] = 1
return vector
training_data = [(to_char_vector_sequence(word), to_word_vector(word))
for word in text.split()]
n = NoOutputLstm(len(index_to_char), len(index_to_word))
for i in range(1000):
for char_vectors, word_vector in training_data:
intermediate_results = {}
h_last = n.forward_prop(char_vectors,
np.zeros(len(index_to_word)),
intermediate_results)
n.back_prop(ce_err_prime(h_last, word_vector),
intermediate_results)
n.train(0.1, intermediate_results)
if i % 200 == 0:
total_err = 0
for char_vectors, word_vector in training_data:
h = n.activate(char_vectors, np.zeros(len(index_to_word)))
total_err += mathutils.mean_squared_error(h, word_vector)
print((total_err / len(training_data)))
result = n.activate(to_char_vector_sequence("infer"),
np.zeros(len(index_to_word)))
self.assertEquals("infer", index_to_word[np.argmax(result)])
def test_learn_word_vectors_from_char_vector_sequence(self):
text = "please learn how to infer word vectors from sequences of character vectors"
index_to_word = list(set(text.split()))
index_to_char = list(set(text))
word_to_index = {word: index for index, word in enumerate(index_to_word)}
char_to_index = {word: index for index, word in enumerate(index_to_char)}
def to_char_vector_sequence(word):
sequence = []
for char in word:
vector = np.ones(len(char_to_index)) * -1
vector[char_to_index[char]] = 1
sequence.append(vector)
sequence.append(np.zeros(len(char_to_index)))
return np.asarray(sequence)
def to_word_vector(word):
vector = np.ones(len(word_to_index)) * -1
vector[word_to_index[word]] = 1
return vector
training_data = [(to_char_vector_sequence(word), to_word_vector(word)) for word in text.split()]
n = NoOutputLstm(len(index_to_char), len(index_to_word))
for i in range(1000):
for char_vectors, word_vector in training_data:
intermediate_results = {}
h_last = n.forward_prop(char_vectors, np.zeros(len(index_to_word)), intermediate_results)
n.back_prop(ce_err_prime(h_last, word_vector), intermediate_results)
n.train(0.1, intermediate_results)
if i % 200 == 0:
total_err = 0
for char_vectors, word_vector in training_data:
h = n.activate(char_vectors, np.zeros(len(index_to_word)))
total_err += mathutils.mean_squared_error(h, word_vector)
print(total_err/len(training_data))
result = n.activate(to_char_vector_sequence("infer"), np.zeros(len(index_to_word)))
self.assertEquals("infer", index_to_word[np.argmax(result)])
