Модель Кераса для двумерного ввода - PullRequest
Новая
       1

Модель Кераса для двумерного ввода

0 голосов
/ 29 января 2019

Я пытаюсь адаптировать учебник keras о ценах на жилье, чтобы оценить позиции в настольной игре.Проблема в том, что позиции настольной игры двумерные, и это заставляет keras жаловаться.

Вот некоторый код, основанный на руководстве, который обрабатывает некоторые фиктивные данные, сгенерированные из линейного уравнения. 

import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold

# fix random seed for reproducibility
seed = 1
np.random.seed(seed)

# Generate dataset with linear outputs.
sample_count = 1000
column_count = 5
X = np.random.uniform(size=sample_count * column_count)
X.shape = (sample_count, column_count)
Y = 2*X[:, 0] + X[:, 1] + X[:, 2] + 11*X[:, 3] + 3*X[:, 4]


# define base model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Dense(column_count * 2,
                    input_dim=column_count,
                    kernel_initializer='normal',
                    activation='relu'))
    model.add(Dense(1, kernel_initializer='normal'))
    # Compile model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model


# evaluate model with standardized dataset
estimator = KerasRegressor(build_fn=baseline_model, epochs=100, batch_size=5, verbose=0)

kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(estimator, X, Y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))

estimator.fit(X, Y)

test_samples = np.identity(column_count)
predictions = estimator.predict(test_samples)
print(predictions)

Это прекрасно работает, но не тогда, когда я пытаюсь что-то эквивалентное с двумерными данными.Вот двумерный код: 

import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold

# fix random seed for reproducibility
seed = 1
np.random.seed(seed)

# Generate dataset with linear outputs.
sample_count = 1000
row_count = 2
column_count = 3
X = np.random.uniform(size=sample_count * row_count * column_count)
X = X.reshape(sample_count, row_count, column_count)
Y = 2*X[:, 0, 0] + X[:, 0, 1] + 2*X[:, 0, 2] + 11*X[:, 1, 0] + 3*X[:, 1, 1]
Y = Y.reshape(sample_count, 1)


# define base model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Dense(row_count * column_count * 2,
                    input_shape=(row_count, column_count),
                    kernel_initializer='normal',
                    activation='relu'))
    model.add(Dense(1, kernel_initializer='normal'))
    # Compile model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model


# evaluate model with standardized dataset
estimator = KerasRegressor(build_fn=baseline_model, epochs=100, batch_size=5, verbose=0)

kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(estimator, X, Y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))

estimator.fit(X, Y)

test_samples = np.zeros((row_count*column_count, row_count, column_count))
for sample_num, (row_num, column_num) in enumerate((row_num, column_num)
                                                   for row_num in range(row_count)
                                                   for column_num in range(column_count)):
    test_samples[sample_num, row_num, column_num] = 1
predictions = estimator.predict(test_samples)
print(predictions)

Когда я запускаю этот код, я получаю эту ошибку: 

Traceback (most recent call last):
  File "/home/don/PycharmProjects/ml_tutorial/ml_tutorial/run_linear2.py", line 40, in <module>
    results = cross_val_score(estimator, X, Y, cv=kfold)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 402, in cross_val_score
    error_score=error_score)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 240, in cross_validate
    for train, test in cv.split(X, y, groups))
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 917, in __call__
    if self.dispatch_one_batch(iterator):
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 759, in dispatch_one_batch
    self._dispatch(tasks)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 716, in _dispatch
    job = self._backend.apply_async(batch, callback=cb)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 182, in apply_async
    result = ImmediateResult(func)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 549, in __init__
    self.results = batch()
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 225, in __call__
    for func, args, kwargs in self.items]
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 225, in <listcomp>
    for func, args, kwargs in self.items]
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 528, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/keras/wrappers/scikit_learn.py", line 152, in fit
    history = self.model.fit(x, y, **fit_args)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/keras/engine/training.py", line 952, in fit
    batch_size=batch_size)
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/keras/engine/training.py", line 789, in _standardize_user_data
    exception_prefix='target')
  File "/home/don/.local/share/virtualenvs/ml_tutorial-3a_885qf/lib/python3.6/site-packages/keras/engine/training_utils.py", line 128, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking target: expected dense_2 to have 3 dimensions, but got array with shape (900, 1)

Как я могу убедить модель принять двумерные входные данные?

1 Ответ

0 голосов
/ 29 января 2019

Основываясь на аналогичном обсуждении в выпуске GitHub , вы можете просто добавить слой Flatten(), чтобы уменьшить входные размеры. 

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Flatten
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold

# fix random seed for reproducibility
seed = 1
np.random.seed(seed)

# Generate dataset with linear outputs.
sample_count = 1000
row_count = 2
column_count = 3
X = np.random.uniform(size=sample_count * row_count * column_count)
X = X.reshape(sample_count, row_count, column_count)
Y = 2*X[:, 0, 0] + X[:, 0, 1] + 2*X[:, 0, 2] + 11*X[:, 1, 0] + 3*X[:, 1, 1]
Y = Y.reshape(sample_count, 1)


# define base model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Dense(row_count * column_count * 2,
                    input_shape=(row_count, column_count),
                    kernel_initializer='normal',
                    activation='relu'))
    model.add(Flatten())
    model.add(Dense(1, kernel_initializer='normal'))
    # Compile model
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model


# evaluate model with standardized dataset
estimator = KerasRegressor(build_fn=baseline_model, epochs=100, batch_size=5, verbose=0)

kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(estimator, X, Y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))

estimator.fit(X, Y)

test_samples = np.zeros((row_count*column_count, row_count, column_count))
for sample_num, (row_num, column_num) in enumerate((row_num, column_num)
                                                   for row_num in range(row_count)
                                                   for column_num in range(column_count)):
    test_samples[sample_num, row_num, column_num] = 1
predictions = estimator.predict(test_samples)
print(predictions)

Я думаю, что мне нужноиспользуйте другие слои, такие как Conv2D, чтобы на самом деле воспользоваться двумерными отношениями, но это избавит меня от ошибки.

Добро пожаловать на сайт PullRequest, где вы можете задавать вопросы и получать ответы от других членов сообщества.

Нет похожих вопросов

...