我试图将SVM与我的CNN代码结合使用，所以我使用了this代码。但是，在重塑目标以适合SVM的过程中遇到了一些问题。
原始的X_train.shape，X_test.shape，y_train.shape，y_test.shape分别是：
(2480, 1, 513, 125)
(560, 1, 513, 125)
(2480, 2)
(560, 2)
之后，当我尝试此操作时：
exTrain = getFeature([X_train[:50], 0])[0]
exTest = getFeature([X_test[:10], 0])[0]
y_train = y_train[:50].reshape(y_train[:50].shape[0],)
我收到此错误消息：
ValueError：无法将大小为100的数组重塑为形状（50，）
这是我的代码
import os
import numpy as np
from sklearn.metrics import confusion_matrix
from plot_metrics import plot_accuracy, plot_loss, plot_roc_curve
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
K.set_image_dim_ordering('th')
np.random.seed(15)
"""
CNN used to classify spectrograms of normal participants (0) or depressed
participants (1). Using Theano backend and Theano image_dim_ordering:
(# channels, # images, # rows, # cols)
(1, 3040, 513, 125)
"""
def preprocess(X_train, X_test):
"""
Convert from float64 to float32 and normalize normalize to decibels
relative to full scale (dBFS) for the 4 sec clip.
"""
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train = np.array([(X - X.min()) / (X.max() - X.min()) for X in X_train])
X_test = np.array([(X - X.min()) / (X.max() - X.min()) for X in X_test])
return X_train, X_test
def prep_train_test(X_train, y_train, X_test, y_test, nb_classes):
"""
Prep samples ands labels for Keras input by noramalzing and converting
labels to a categorical representation.
"""
print('Train on {} samples, validate on {}'.format(X_train.shape[0],
X_test.shape[0]))
# normalize to dBfS
X_train, X_test = preprocess(X_train, X_test)
# Convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
return X_train, X_test, Y_train, Y_test
def keras_img_prep(X_train, X_test, img_dep, img_rows, img_cols):
"""
Reshape feature matrices for Keras' expexcted input dimensions.
For 'th' (Theano) dim_order, the model expects dimensions:
(# channels, # images, # rows, # cols).
"""
if K.image_dim_ordering() == 'th':
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
return X_train, X_test, input_shape
def cnn(X_train, y_train, X_test, y_test, batch_size,
nb_classes, epochs, input_shape):
"""
The Convolutional Neural Net architecture for classifying the audio clips
as normal (0) or depressed (1).
"""
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='valid', strides=1,
input_shape=input_shape, activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 3), strides=(1, 3)))
model.add(Conv2D(32, (1, 3), padding='valid', strides=1,
input_shape=input_shape, activation='relu'))
model.add(MaxPooling2D(pool_size=(1, 3), strides=(1, 3)))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
history = model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs,
verbose=1, validation_data=(X_test, y_test))
# Evaluate accuracy on test and train sets
score_train = model.evaluate(X_train, y_train, verbose=0)
print('Train accuracy:', score_train[1])
score_test = model.evaluate(X_test, y_test, verbose=0)
print('Test accuracy:', score_test[1])
return model, history
def model_performance(model, X_train, X_test, y_train, y_test):
"""
Evaluation metrics for network performance.
"""
y_test_pred = model.predict_classes(X_test)
y_train_pred = model.predict_classes(X_train)
y_test_pred_proba = model.predict_proba(X_test)
y_train_pred_proba = model.predict_proba(X_train)
# Converting y_test back to 1-D array for confusion matrix computation
y_test_1d = y_test[:, 1]
# Computing confusion matrix for test dataset
conf_matrix = standard_confusion_matrix(y_test_1d, y_test_pred)
print("Confusion Matrix:")
print(conf_matrix)
return y_train_pred, y_test_pred, y_train_pred_proba, \
y_test_pred_proba, conf_matrix
def standard_confusion_matrix(y_test, y_test_pred):
"""
Make confusion matrix with format:
-----------
| TP | FP |
-----------
| FN | TN |
-----------
Parameters
----------
y_true : ndarray - 1D
y_pred : ndarray - 1D
Returns
-------
ndarray - 2D
"""
[[tn, fp], [fn, tp]] = confusion_matrix(y_test, y_test_pred)
return np.array([[tp, fp], [fn, tn]])
if __name__ == '__main__':
print('Retrieving locally')
X_train = np.load('E:/depression detection/data/processed/train_samples.npz')
y_train = np.load('E:/depression detection/data/processed/train_labels.npz')
X_test = np.load('E:/depression detection/data/processed/test_samples.npz')
y_test = np.load('E:/depression detection/data/processed/test_labels.npz')
X_train, y_train, X_test, y_test = \
X_train['arr_0'], y_train['arr_0'], X_test['arr_0'], y_test['arr_0']
# CNN parameters
batch_size = 32
nb_classes = 2
epochs = 1
# normalalize data and prep for Keras
print('Processing images for Keras...')
X_train, X_test, y_train, y_test = prep_train_test(X_train, y_train,
X_test, y_test,
nb_classes=nb_classes)
# 513x125x1 for spectrogram with crop size of 125 pixels
img_rows, img_cols, img_depth = X_train.shape[1], X_train.shape[2], 1
# reshape image input for Keras
# used Theano dim_ordering (th), (# chans, # images, # rows, # cols)
X_train, X_test, input_shape = keras_img_prep(X_train, X_test, img_depth,
img_rows, img_cols)
# run CNN
print('Fitting model...')
model, history = cnn(X_train, y_train, X_test, y_test, batch_size,
nb_classes, epochs, input_shape)
# evaluate model
print('Evaluating model...')
y_train_pred, y_test_pred, y_train_pred_proba, y_test_pred_proba, \
conf_matrix = model_performance(model, X_train, X_test, y_train, y_test)
for l in range(len(model.layers)):
print(l, model.layers[l])
# feature extraction layer
getFeature = K.function([model.layers[0].input, K.learning_phase()],
[model.layers[7].output])
# classification layer
getPrediction = K.function([model.layers[8].input, K.learning_phase()],
[model.layers[9].output])
exTrain = getFeature([X_train[:50], 0])[0]
exTest = getFeature([X_test[:10], 0])[0]
y_train = y_train[:50].reshape(y_train[:50].shape[0],)
y_test = y_test[:10]
print(exTrain.shape, exTest.shape, y_train.shape, y_test.shape)
from sklearn.svm import SVC
clf = SVC(gamma='auto')
clf.fit(exTrain, y_train)
score_train = model.evaluate(exTrain, y_train, verbose=0)
print('Train accuracy:', score_train[1])
score_test = model.evaluate(exTest, y_test, verbose=0)
print('Test accuracy:', score_test[1])
我不知道如何解决此问题。