Я тренировал эту модель с кератами для генератора текста
# Small LSTM Network to Generate Text for Alice in Wonderland
import numpy
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import LSTM
from keras.callbacks import ModelCheckpoint
from keras.utils import np_utils
# load ascii text and covert to lowercase
filename = "lyrics_small.txt"
raw_text = open(filename).read()
raw_text = raw_text.lower()
# create mapping of unique chars to integers
chars = sorted(list(set(raw_text)))
char_to_int = dict((c, i) for i, c in enumerate(chars))
# summarize the loaded data
n_chars = len(raw_text)
n_vocab = len(chars)
print ("Total Characters: ", n_chars)
print ("Total Vocab: ", n_vocab)
# prepare the dataset of input to output pairs encoded as integers
seq_length = 100
dataX = []
dataY = []
for i in range(0, n_chars - seq_length, 1):
seq_in = raw_text[i:i + seq_length]
seq_out = raw_text[i + seq_length]
dataX.append([char_to_int[char] for char in seq_in])
dataY.append(char_to_int[seq_out])
n_patterns = len(dataX)
print ("Total Patterns: ", n_patterns)
# reshape X to be [samples, time steps, features]
X = numpy.reshape(dataX, (n_patterns, seq_length, 1))
# normalize
X = X / float(n_vocab)
# one hot encode the output variable
y = np_utils.to_categorical(dataY)
model = Sequential()
model.add(LSTM(256, input_shape=(X.shape[1], X.shape[2]), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(256))
model.add(Dropout(0.2))
model.add(Dense(y.shape[1], activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam')
# define the checkpoint
filepath="weights-improvement-{epoch:02d}-{loss:.4f}.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]
# fit the model
model.fit(X, y, epochs=20, batch_size=128, callbacks=callbacks_list)
как только он закончил работать, я понял, что на самом деле модель не спасла.
Не проблема, потому чтовы можете загрузить весовые коэффициенты в модель и использовать ее, и в этом блоге содержались инструкции об этом
# load ascii text and covert to lowercase
filename = "lyrics_small.txt"
raw_text = open(filename).read()
raw_text = raw_text.lower()
# create mapping of unique chars to integers
chars = sorted(list(set(raw_text)))
char_to_int = dict((c, i) for i, c in enumerate(chars))
# summarize the loaded data
n_chars = len(raw_text)
n_vocab = len(chars)
print ("Total Characters: ", n_chars)
print ("Total Vocab: ", n_vocab)
# prepare the dataset of input to output pairs encoded as integers
seq_length = 100
dataX = []
dataY = []
for i in range(0, n_chars - seq_length, 1):
seq_in = raw_text[i:i + seq_length]
seq_out = raw_text[i + seq_length]
dataX.append([char_to_int[char] for char in seq_in])
dataY.append(char_to_int[seq_out])
n_patterns = len(dataX)
print ("Total Patterns: ", n_patterns)
# reshape X to be [samples, time steps, features]
X = numpy.reshape(dataX, (n_patterns, seq_length, 1))
# normalize
X = X / float(n_vocab)
# one hot encode the output variable
y = np_utils.to_categorical(dataY)
model = Sequential()
model.add(LSTM(256, input_shape=(X.shape[1], X.shape[2]), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(256))
model.add(Dropout(0.2))
model.add(Dense(y.shape[1], activation='softmax'))
# load the network weights
filename = "weights-improvement-17-1.7150.hdf5"
model.load_weights(filename)
model.compile(loss='categorical_crossentropy', optimizer='adam')
# pick a random seed
start = numpy.random.randint(0, len(dataX)-1)
pattern = dataX[start]
print ("Seed:")
print ("\"", ''.join([int_to_char[value] for value in pattern]), "\"")
# generate characters
for i in range(1000):
x = numpy.reshape(pattern, (1, len(pattern), 1))
x = x / float(n_vocab)
prediction = model.predict(x, verbose=0)
index = numpy.argmax(prediction)
result = int_to_char[index]
seq_in = [int_to_char[value] for value in pattern]
sys.stdout.write(result)
pattern.append(index)
pattern = pattern[1:len(pattern)]
print ("\nDone.")
, но при запуске модели выдается ошибка несовместимости
Using TensorFlow backend.
Total Characters: 1571440
Total Vocab: 124
Total Patterns: 1571340
Traceback (most recent call last):
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1628, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension 1 in both shapes must be equal, but are 124 and 121. Shapes are [256,124] and [256,121]. for 'Assign_6' (op: 'Assign') with input shapes: [256,124], [256,121].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "new_model_trained.py", line 58, in <module>
model.load_weights(filename)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/keras/engine/network.py", line 1166, in load_weights
f, self.layers, reshape=reshape)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/keras/engine/saving.py", line 1058, in load_weights_from_hdf5_group
K.batch_set_value(weight_value_tuples)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2465, in batch_set_value
assign_op = x.assign(assign_placeholder)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/ops/variables.py", line 1718, in assign
name=name)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 221, in assign
validate_shape=validate_shape)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/ops/gen_state_ops.py", line 61, in assign
use_locking=use_locking, name=name)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1792, in __init__
control_input_ops)
File "/home/sam/code/envs/data/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1631, in _create_c_op
raise ValueError(str(e))
ValueError: Dimension 1 in both shapes must be equal, but are 124 and 121. Shapes are [256,124] and [256,121]. for 'Assign_6' (op: 'Assign') with input shapes: [256,124], [256,121].
, посколькумодель получает это input_shape из формы X, что приводит меня к предположению, что модель не разделяет содержимое согласованным образом.
Есть ли способ исправить это?