运行环境 pycharm2019.2.3
python 3.7
TensorFlow 2.0
代码如下
import tensorflow as tf
import numpy as np
class DataLoader():
def __init__(self):
path = tf.keras.utils.get_file('nietzsche.txt',
origin='https://s3.amazonaws.com/text-datasets/nietzsche.txt')
with open(path, encoding='utf-8') as f:
self.raw_text = f.read().lower()
self.chars = sorted(list(set(self.raw_text)))
self.char_indices = dict((c, i) for i, c in enumerate(self.chars))
self.indices_char = dict((i, c) for i, c in enumerate(self.chars))
self.text = [self.char_indices[c] for c in self.raw_text]
def get_batch(self, seq_length, batch_size):
seq = []
next_char = []
for i in range(batch_size):
index = np.random.randint(0, len(self.text) - seq_length)
seq.append(self.text[index:index+seq_length])
next_char.append(self.text[index+seq_length])
return np.array(seq), np.array(next_char) # [batch_size, seq_length], [num_batch]
class RNN(tf.keras.Model):
def __init__(self, num_chars, batch_size, seq_length):
super().__init__()
self.num_chars = num_chars
self.seq_length = seq_length
self.batch_size = batch_size
self.cell = tf.keras.layers.LSTMCell(units=256)
self.dense = tf.keras.layers.Dense(units=self.num_chars)
def call(self, inputs, from_logits=False):
inputs = tf.one_hot(inputs, depth=self.num_chars) # [batch_size, seq_length, num_chars]
state = self.cell.get_initial_state(batch_size=self.batch_size, dtype=tf.float32)
for t in range(self.seq_length):
output, state = self.cell(inputs[:, t, :], state)
logits = self.dense(output)
if from_logits:
return logits
else:
return tf.nn.softmax(logits)
num_batches = 10
seq_length = 40
batch_size = 50
learning_rate = 1e-3
data_loader = DataLoader()
model = RNN(num_chars=len(data_loader.chars), batch_size=batch_size, seq_length=seq_length)
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
for batch_index in range(num_batches):
X, y = data_loader.get_batch(seq_length, batch_size)
with tf.GradientTape() as tape:
y_pred = model(X)
loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=y, y_pred=y_pred)
loss = tf.reduce_mean(loss)
print("batch %d: loss %f" % (batch_index, loss.numpy()))
grads = tape.gradient(loss, model.variables)
optimizer.apply_gradients(grads_and_vars=zip(grads, model.variables))
def predict(self, inputs, temperature=1.):
batch_size, _ = tf.shape(inputs)
logits = self(inputs, from_logits=True)
print(logits)
print(temperature)
prob = tf.nn.softmax(logits / temperature).numpy()
return np.array([np.random.choice(self.num_chars, p=prob[i, :])
for i in range(batch_size.numpy())])
X_, _ = data_loader.get_batch(seq_length, 1)
for diversity in [0.2, 0.5, 1.0, 1.2]:
X = X_
print("diversity %f:" % diversity)
for t in range(400):
y_pred = model.predict(X, diversity)
print(data_loader.indices_char[y_pred[0]], end='', flush=True)
X = np.concatenate([X[:, 1:], np.expand_dims(y_pred, axis=1)], axis=-1)
print("\n")
报错：
runfile('F:/pyth/pj3/study3.py', wdir='F:/pyth/pj3')
batch 0: loss 4.044459
batch 1: loss 4.025946
batch 2: loss 4.001545
batch 3: loss 3.980800
batch 4: loss 3.945248
batch 5: loss 3.867068
batch 6: loss 3.684950
batch 7: loss 3.236459
batch 8: loss 3.574704
batch 9: loss 3.551273
diversity 0.200000:
Traceback (most recent call last):
File "<input>", line 1, in <module>
File "D:\Program Files\JetBrains\PyCharm 2019.2.3\helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars) # execute the script
File "D:\Program Files\JetBrains\PyCharm 2019.2.3\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "F:/pyth/pj3/study3.py", line 93, in <module>
y_pred = model.predict(X, diversity)
File "D:\ProgramData\Anaconda3\envs\kingtf2\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 909, in predict
use_multiprocessing=use_multiprocessing)
File "D:\ProgramData\Anaconda3\envs\kingtf2\lib\site-packages\tensorflow_core\python\keras\engine\training_arrays.py", line 722, in predict
callbacks=callbacks)
File "D:\ProgramData\Anaconda3\envs\kingtf2\lib\site-packages\tensorflow_core\python\keras\engine\training_arrays.py", line 362, in model_iteration
batch_ids = index_array[batch_start:batch_end]
TypeError: slice indices must be integers or None or have an __index__ method
WARNING:tensorflow:Tensor._shape is private, use Tensor.shape instead. Tensor._shape will eventually be removed.
WARNING:tensorflow:Tensor._shape is private, use Tensor.shape instead. Tensor._shape will eventually be removed.
可能有问题的位置：
for diversity in [0.2, 0.5, 1.0, 1.2]:
X = X_
print("diversity %f:" % diversity)
for t in range(400):
y_pred = model.predict(X, diversity)
print(data_loader.indices_char[y_pred[0]], end='', flush=True)
X = np.concatenate([X[:, 1:], np.expand_dims(y_pred, axis=1)], axis=-1)
print("\n")
def predict(self, inputs, temperature=1.):
batch_size, _ = tf.shape(inputs)
logits = self(inputs, from_logits=True)
prob = tf.nn.softmax(logits / temperature).numpy()
return np.array([np.random.choice(self.num_chars, p=prob[i, :])
for i in range(batch_size.numpy())])
