Python Keras LSTM“检查输入时出错”
Python Keras LSTM " Error when checking input"
我正在尝试训练 LSTM RNN。这是我第一次尝试并使用 Keras。我使用了指南来编写此代码。
这是数据示例：
lat long datetime id trip_id mode_cat
0 39.979973 116.305745 2011-08-27 06:13:01 20 1 1
1 39.979957 116.305688 2011-08-27 06:13:02 20 1 1
2 39.979960 116.305693 2011-08-27 06:13:03 20 1 1
3 39.979970 116.305717 2011-08-27 06:13:04 20 1 1
4 39.979985 116.305732 2011-08-27 06:13:05 20 1 1
其中 lat, long, datetime, id，trip_id 是输入，mode_cat 是输出（输出是二进制的）。
这是我创建和训练 RNN 的代码部分：
def evaluate_model(trainX, trainy, testX, testy):
verbose, epochs, batch_size = 0, 15, 64
n_timesteps, n_features, n_outputs = trainX.shape[0], trainX.shape[1], 1
model = Sequential()
print("adding LSTM")
model.add(LSTM(1, input_shape=(n_timesteps,n_features), return_sequences=True))
print("adding dropout")
model.add(Dropout(0.5))
print("adding dense")
model.add(Dense(100, activation='relu'))
print("adding dense")
model.add(Dense(n_outputs, activation='softmax'))
print("adding compile")
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
# fit network
model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=verbose)
# evaluate model
_, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
return accuracy
def run_experiment(repeats=10):
# repeat experiment
scores = list()
for r in range(repeats):
score = evaluate_model(train_x, train_y, test_x, test_y)
score = score * 100.0
print('>#%d: %.3f' % (r+1, score))
scores.append(score)
# summarize results
summarize_results(scores)
run_experiment()
我得到以下结果：
adding LSTM
adding dropout
adding dense
adding dense
adding compile
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_1 (LSTM) (None, 455414, 1) 28
_________________________________________________________________
dropout_1 (Dropout) (None, 455414, 1) 0
_________________________________________________________________
dense_1 (Dense) (None, 455414, 100) 200
_________________________________________________________________
dense_2 (Dense) (None, 455414, 1) 101
=================================================================
Total params: 329
Trainable params: 329
Non-trainable params: 0
_________________________________________________________________
None
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-8-5d4acc2b23d8> in <module>()
31 summarize_results(scores)
32
---> 33 run_experiment()
<ipython-input-8-5d4acc2b23d8> in run_experiment(repeats)
24 scores = list()
25 for r in range(repeats):
---> 26 score = evaluate_model(train_x, train_y, test_x, test_y)
27 score = score * 100.0
28 print('>#%d: %.3f' % (r+1, score))
<ipython-input-8-5d4acc2b23d8> in evaluate_model(trainX, trainy, testX, testy)
15 print(model.summary())
16 # fit network
---> 17 model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=verbose)
18 # evaluate model
19 _, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
~\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
1152 sample_weight=sample_weight,
1153 class_weight=class_weight,
-> 1154 batch_size=batch_size)
1155
1156 # Prepare validation data.
~\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
577 feed_input_shapes,
578 check_batch_axis=False, # Don't enforce the batch size.
--> 579 exception_prefix='input')
580
581 if y is not None:
~\Anaconda3\lib\site-packages\keras\engine\training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
133 ': expected ' + names[i] + ' to have ' +
134 str(len(shape)) + ' dimensions, but got array '
--> 135 'with shape ' + str(data_shape))
136 if not check_batch_axis:
137 data_shape = data_shape[1:]
ValueError: Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (455414, 5)
请指教！
为 RNN 提供数据与处理序列的其他网络略有不同。
您的代码中的问题是数据集格式。 RNN 的输入应该是形状为 [batch, timesteps, feature] 1
的 3D 张量
由于您有时间序列数据集，因此您应该使用移动 window 方案
预处理输入数据
您应该检查 this tutorial 时间序列预测，他们在其中实施了 window 方案，如下所示：
def multivariate_data(dataset, target, start_index, end_index, history_size,
target_size, step, single_step=False):
data = []
labels = []
start_index = start_index + history_size
if end_index is None:
end_index = len(dataset) - target_size
for i in range(start_index, end_index):
indices = range(i-history_size, i, step)
data.append(dataset[indices])
if single_step:
labels.append(target[i+target_size])
else:
labels.append(target[i:i+target_size])
return np.array(data), np.array(labels)
past_history = 720
future_target = 72
STEP = 6
x_train_single, y_train_single = multivariate_data(dataset, dataset[:, 1], 0,
TRAIN_SPLIT, past_history,
future_target, STEP,
single_step=True)
x_val_single, y_val_single = multivariate_data(dataset, dataset[:, 1],
TRAIN_SPLIT, None, past_history,
future_target, STEP,
single_step=True)
这是移动 window 过程的图示（取自此 paper）
您的问题不完全是时间序列预测，因此您应该根据您的问题调整该教程中的代码。
它应该是这样的：
def moving_window(dataset, past_history):
data, labels = [], []
for i in range(past_history, len(dataset)):
indices = range(i-past_history, i)
data.append(dataset[['lat', 'long', 'id', 'trip_id']].values[indices])
label.append(dataset['mode_cat'][i])
return np.array(data), np.array(labels)
PAST_HISTORY = 60
X, y = moving_window(dataset, PAST_HISTORY)
PAST_HISTORY 是一个应该调整的超参数。
希望对您有所帮助！ :)
我正在尝试训练 LSTM RNN。这是我第一次尝试并使用 Keras。我使用了指南来编写此代码。
这是数据示例：
lat long datetime id trip_id mode_cat
0 39.979973 116.305745 2011-08-27 06:13:01 20 1 1
1 39.979957 116.305688 2011-08-27 06:13:02 20 1 1
2 39.979960 116.305693 2011-08-27 06:13:03 20 1 1
3 39.979970 116.305717 2011-08-27 06:13:04 20 1 1
4 39.979985 116.305732 2011-08-27 06:13:05 20 1 1
其中 lat, long, datetime, id，trip_id 是输入，mode_cat 是输出（输出是二进制的）。
这是我创建和训练 RNN 的代码部分：
def evaluate_model(trainX, trainy, testX, testy):
verbose, epochs, batch_size = 0, 15, 64
n_timesteps, n_features, n_outputs = trainX.shape[0], trainX.shape[1], 1
model = Sequential()
print("adding LSTM")
model.add(LSTM(1, input_shape=(n_timesteps,n_features), return_sequences=True))
print("adding dropout")
model.add(Dropout(0.5))
print("adding dense")
model.add(Dense(100, activation='relu'))
print("adding dense")
model.add(Dense(n_outputs, activation='softmax'))
print("adding compile")
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
# fit network
model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=verbose)
# evaluate model
_, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
return accuracy
def run_experiment(repeats=10):
# repeat experiment
scores = list()
for r in range(repeats):
score = evaluate_model(train_x, train_y, test_x, test_y)
score = score * 100.0
print('>#%d: %.3f' % (r+1, score))
scores.append(score)
# summarize results
summarize_results(scores)
run_experiment()
我得到以下结果：
adding LSTM
adding dropout
adding dense
adding dense
adding compile
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_1 (LSTM) (None, 455414, 1) 28
_________________________________________________________________
dropout_1 (Dropout) (None, 455414, 1) 0
_________________________________________________________________
dense_1 (Dense) (None, 455414, 100) 200
_________________________________________________________________
dense_2 (Dense) (None, 455414, 1) 101
=================================================================
Total params: 329
Trainable params: 329
Non-trainable params: 0
_________________________________________________________________
None
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-8-5d4acc2b23d8> in <module>()
31 summarize_results(scores)
32
---> 33 run_experiment()
<ipython-input-8-5d4acc2b23d8> in run_experiment(repeats)
24 scores = list()
25 for r in range(repeats):
---> 26 score = evaluate_model(train_x, train_y, test_x, test_y)
27 score = score * 100.0
28 print('>#%d: %.3f' % (r+1, score))
<ipython-input-8-5d4acc2b23d8> in evaluate_model(trainX, trainy, testX, testy)
15 print(model.summary())
16 # fit network
---> 17 model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=verbose)
18 # evaluate model
19 _, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
~\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
1152 sample_weight=sample_weight,
1153 class_weight=class_weight,
-> 1154 batch_size=batch_size)
1155
1156 # Prepare validation data.
~\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
577 feed_input_shapes,
578 check_batch_axis=False, # Don't enforce the batch size.
--> 579 exception_prefix='input')
580
581 if y is not None:
~\Anaconda3\lib\site-packages\keras\engine\training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
133 ': expected ' + names[i] + ' to have ' +
134 str(len(shape)) + ' dimensions, but got array '
--> 135 'with shape ' + str(data_shape))
136 if not check_batch_axis:
137 data_shape = data_shape[1:]
ValueError: Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (455414, 5)
请指教！
为 RNN 提供数据与处理序列的其他网络略有不同。
您的代码中的问题是数据集格式。 RNN 的输入应该是形状为 [batch, timesteps, feature] 1
由于您有时间序列数据集，因此您应该使用移动 window 方案
预处理输入数据您应该检查 this tutorial 时间序列预测，他们在其中实施了 window 方案，如下所示：
def multivariate_data(dataset, target, start_index, end_index, history_size,
target_size, step, single_step=False):
data = []
labels = []
start_index = start_index + history_size
if end_index is None:
end_index = len(dataset) - target_size
for i in range(start_index, end_index):
indices = range(i-history_size, i, step)
data.append(dataset[indices])
if single_step:
labels.append(target[i+target_size])
else:
labels.append(target[i:i+target_size])
return np.array(data), np.array(labels)
past_history = 720
future_target = 72
STEP = 6
x_train_single, y_train_single = multivariate_data(dataset, dataset[:, 1], 0,
TRAIN_SPLIT, past_history,
future_target, STEP,
single_step=True)
x_val_single, y_val_single = multivariate_data(dataset, dataset[:, 1],
TRAIN_SPLIT, None, past_history,
future_target, STEP,
single_step=True)
这是移动 window 过程的图示（取自此 paper）
您的问题不完全是时间序列预测，因此您应该根据您的问题调整该教程中的代码。 它应该是这样的：
def moving_window(dataset, past_history):
data, labels = [], []
for i in range(past_history, len(dataset)):
indices = range(i-past_history, i)
data.append(dataset[['lat', 'long', 'id', 'trip_id']].values[indices])
label.append(dataset['mode_cat'][i])
return np.array(data), np.array(labels)
PAST_HISTORY = 60
X, y = moving_window(dataset, PAST_HISTORY)
PAST_HISTORY 是一个应该调整的超参数。
希望对您有所帮助！ :)