def initialize_chatbot():
#print("initializing chatbot... \n")
#print("Loading dictionary...")
with open("model_data/vocab_dict.p", 'rb') as fp:
vocab = pickle.load(fp)
#print(f"Loaded {len(vocab)} words")
#print("making sample embedding matrix...")
sample_emb = tf.zeros((len(vocab), 100))
""" ENCODER WORK """
#print("Initializing Encoder...")
encoder = Encoder(len(vocab),
100,
500,
128,
sample_emb,
num_layers=3,
drop_prob=0.1)
#print("Testing Encoder...")
sample_hidden = encoder.initialize_hidden_state()
ex_input_bt = tf.zeros((128, 25))
sample_output, sample_hidden = encoder(ex_input_bt, sample_hidden)
assert sample_output.shape == (128, 25, 500)
assert sample_hidden.shape == (128, 500)
#print("Loading up encoder...")
encoder.load_weights("model_data/encoder_gpu.h5")
""" DECODER WORK """
#print("Initializing Decoder...")
decoder = Decoder(len(vocab),
100,
500,
128,
sample_emb,
num_layers=3,
drop_prob=0.1)
#print("Testing Decoder...")
sample_decoder_output, _, _ = decoder(tf.random.uniform((128, 1)),
sample_hidden, sample_output)
assert sample_decoder_output.shape == (128, len(vocab))
#print("Loading up decoder...")
decoder.load_weights("model_data/decoder_gpu.h5")
# inverse vocabulary
inv_vocab = {v: k for k, v in vocab.items()}
""" Some variables"""
pad_token = 0
sos_token = 1
eos_token = 2
units = 500
maxl = 25
"""Processing functions"""
# Convert (or remove accents) sentence to non_accents sentence
def unicodeToAscii(s):
return ''.join(c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn')
# Lowercase, trim, and remove non-letter characters
def normalizeString(s):
s = unicodeToAscii(s.lower().strip())
s = re.sub(r"([.!?])", r" \1", s)
s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
s = re.sub(r"\s+", r" ", s).strip()
return s
return vocab, encoder, decoder, inv_vocab, pad_token, sos_token, eos_token, units, maxl, unicodeToAscii, normalizeString
# print("x_train type:", type(X_train))
# print("x_train shape:", X_train.shape)
db = tf.data.Dataset.from_tensor_slices((X_train, y_train)) # 将数据集转化成tensor
db = db.map(preprocess).shuffle(10000).batch(
batchsz) # 将数据集转化成batch_size的大小为128的数据
# print("db_type:", type(db))
db_test = tf.data.Dataset.from_tensor_slices((X_test, y_test))
db_test = db_test.map(preprocess).batch(batchsz)
encoder = Encoder()
encoder.build(input_shape=(None, 28, 28, 1))
decoder = Decoder()
decoder.build(input_shape=(None, 64, 64, 3))
encoder.load_weights("./encoder_weights.ckpt")
decoder.load_weights('./decoder_weights.ckpt')
#图片的显示
# def generate_plot_image(gen_model, test_noise):
# pre_images = gen_model(test_noise, training=False)
# fig = plt.figure(figsize=(4, 4))
# for i in range(pre_images.shape[0]):
# plt.subplot(4, 4, i+1)
# plt.imshow((pre_images[i, :, :, 0] + 1)/2, cmap='gray')
# plt.axis('off')
# plt.show()
for step, (x, y) in enumerate(db):
en_res = encoder(x)
de_res = decoder(en_res)
