我正在使用带有 TensorFlow 后端的 Keras 做一个神经网络回归问题。我需要一个 RMS 误差值来确定我的模型的性能。不幸的是，这不是 Keras 的开箱即用指标，因此我制作了一个自定义指标。到目前为止，一切都很好。但我的问题是，我在控制台中的 RMS 错误值与我使用 model.evaluate() 并打印到文件时的值不同。关于这是为什么的任何想法？
'''
Trains 7D QuaLiKiz-NN with a single output (efiTG)
'''
from __future__ import print_function
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, BatchNormalization
from keras.optimizers import RMSprop, adam, Adam
from keras.initializers import TruncatedNormal
from keras import regularizers
from keras import backend as K
import pandas
import numpy
import sys
import os
# Define new Metric: rmse = Root Mean Square Error
def rmse(y_true, y_pred):
return K.mean(K.sum(K.square( y_true-y_pred )))
# Gets the current file name. Useful for procedurally generating output/log
files.
file_name = os.path.basename(sys.argv[0][:-3])
# Define neural network parameters
batch_size = 10
#num_classes = 1
epochs = 1
# Load Data (which is in HDF5 or .h5 format)
store = pandas.HDFStore("unstable_training_gen2_7D_nions0_flat_filter7.h5")
target_df = store['efiITG_GB'].to_frame() # This one is relatively easy to
train
input_df = store['input']
# Puts inputs and outputs in the same pandas dataframe.
# Also only keeps overlapping entries.
joined_dataFrame = target_df.join(input_df)
# Remove all negative values
joined_dataFrame = joined_dataFrame[(joined_dataFrame['efiITG_GB']>0)
& (joined_dataFrame['Ati']>0)
& (joined_dataFrame['Ate']>0)
& (joined_dataFrame['An']>0)
& (joined_dataFrame['qx']>0)
& (joined_dataFrame['smag']>0)
& (joined_dataFrame['x']>0)
& (joined_dataFrame['Ti_Te']>0)]
# Shuffles dataset
shuffled_joined_dataFrame =
joined_dataFrame.reindex(numpy.random.permutation(
joined_dataFrame.index))
# Normalizes data (no standardization necessary due to dataset design)
shuffled_joined_dataFrame =
shuffled_joined_dataFrame/shuffled_joined_dataFrame \
.max().astype(numpy.float64)
# Creates a pandas dataframe for the outputs
shuffled_clean_output_df = shuffled_joined_dataFrame['efiITG_GB']
# Creates a pandas dataframe for the inputs
shuffled_clean_input_df = shuffled_joined_dataFrame.drop('efiITG_GB',
axis=1)
# Creates training dataset (90% of total data) for outputs
y_train = shuffled_clean_output_df.iloc[:int(
numpy.round(len(shuffled_clean_output_df)*0.9))]
# Creates training dataset (90% of total data) for inputs
x_train = shuffled_clean_input_df.iloc[:int(
numpy.round(len(shuffled_clean_input_df)*0.9))]
# Creates testing dataset (10% of total data) for outputs
y_test = shuffled_clean_output_df.iloc[int(
numpy.round(len(shuffled_clean_output_df)*0.9)):]
# Creates testing dataset (10% of total data) for inputs
x_test = shuffled_clean_input_df.iloc[int(
numpy.round(len(shuffled_clean_input_df)*0.9)):]
# Deletes pandas dataframes that are no longer needed
del target_df, input_df
# Closes the HDFStore. This is good practice.
store.close()
# Define neural network
model = Sequential()
model.add(Dense(30,
activation='tanh',
kernel_initializer=TruncatedNormal(mean=0.0, stddev=0.05,
seed=None),
kernel_regularizer=regularizers.l2(0.0000001),
input_shape=(7,)))
model.add(Dense(30,
activation='tanh',
kernel_initializer=TruncatedNormal(mean=0.0, stddev=0.05,
seed=None),
kernel_regularizer=regularizers.l2(0.0000001)))
model.add(Dense(30,
activation='tanh',
kernel_initializer=TruncatedNormal(mean=0.0, stddev=0.05,
seed=None),
kernel_regularizer=regularizers.l2(0.0000001)))
model.add(Dense(1,
activation='linear'))
#model.add(keras.layers.normalization.BatchNormalization())
model.summary()
# Add CallBacks (including TensorBoard)
tbCallBack = keras.callbacks.TensorBoard(
log_dir='TensorBoard_logs/' + str(file_name), write_graph=True)
EarlyStoppingCallBack = keras.callbacks.EarlyStopping(
monitor='val_loss', min_delta=0, patience=5, verbose=0, mode='auto')
model.compile(loss='mean_squared_error', #categorical_crossentropy
#optimizer='adam',
optimizer=Adam(lr=0.001, beta_1=0.9, beta_2=0.999),
metrics=['accuracy', "mae", "mean_squared_error", rmse])
history = model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
shuffle=True,
verbose=2,
validation_data=(x_test, y_test),
callbacks=[tbCallBack, EarlyStoppingCallBack])
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
print("score")
print(score)
print("model.metrics_names")
print(model.metrics_names)
# Create output file
OutputFile = open("./Loss-Values/" +str(file_name) +".txt", "w+")
OutputFile.write("Test loss: " + str(score[0]) + "\n")
OutputFile.write("Test accuracy: " + str(score[1]) + "\n")
OutputFile.write("val_mean_absolute_error: " +str(score[2]) + "\n")
OutputFile.write("val_mean_squared_error: " +str(score[3]) + "\n")
OutputFile.write("RMSE: " +str(score[4]) + "\n")
OutputFile.close()
# creates a HDF5 file 'my_model.h5'
model.save("./Saved-Networks/" + str(file_name) +".h5")
我只是为了调试目的而训练 1 个时期。我的控制台输出是：
Epoch 1/1
- 76s - loss: 0.0224 - acc: 1.5288e-06 - mean_absolute_error: 0.1145 -
mean_squared_error: 0.0224 - rmse: 0.2237 - val_loss: 0.0116 - val_acc:
0.0000e+00 - val_mean_absolute_error: 0.0787 - val_mean_squared_error:
0.0116 - val_rmse: 0.1156
Test loss: 0.0115768997629
Test accuracy: 0.0
score
[0.011576899762892088, 0.0, 0.078728127306243859, 0.01156135053880431,
0.36995773298057744]
model.metrics_names
['loss', 'acc', 'mean_absolute_error', 'mean_squared_error', 'rmse']
[Finished in 108.322s]
如您所见，
的值['loss', 'acc', 'mean_absolute_error', 'mean_squared_error', 'rmse']
很好，同意
的价值观Epoch 1/1
- 76s - loss: 0.0224 - acc: 1.5288e-06 - mean_absolute_error: 0.1145 -
mean_squared_error: 0.0224 - rmse: 0.2237 - val_loss: 0.0116 - val_acc:
0.0000e+00 - val_mean_absolute_error: 0.0787 - val_mean_squared_error:
0.0116 - val_rmse: 0.1156
而价值
['loss', 'acc', 'mean_absolute_error', 'mean_squared_error', 'rmse']
不同。知道为什么这个自定义 Keras 指标
rmse附言我的输出文件是：
Test loss: 0.0115768997629
Test accuracy: 0.0
val_mean_absolute_error: 0.0787281273062
val_mean_squared_error: 0.0115613505388
RMSE: 0.369957732981
K.mean(K.sum(K.square( y_true-y_pred )))
不是rmse。这是平方和。
你不需要
K.sum