python - 如何将输入传递给 Keras 中的 2D Conv？

Question

我已经使用 librosa 将语音转换为频谱图。频谱图的形状是 (257, 356)，我已将其 reshape 为 (257, 356, 1)。

我已经创建了一个模型

from keras.models import Sequential
from keras.layers import Dense, Conv2D, Flatten
model = Sequential()
model.add(Conv2D(64, kernel_size=3, activation='relu', input_shape=A.shape))
model.add(Flatten())
model.add(Dense(1, activation='softmax'))

拟合模型时，产生跟随误差

model.fit(A,validation_data=(A2), epochs=3)

其中 A2 是具有以下尺寸的另一个频谱图

ValueError: Error when checking input: expected conv2d_3_input to have 4 dimensions, but got array with shape (257, 356, 1)

模型摘要

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_24 (Conv2D)           (None, 255, 354, 64)      640       
_________________________________________________________________
conv2d_25 (Conv2D)           (None, 253, 352, 32)      18464     
_________________________________________________________________
flatten_11 (Flatten)         (None, 2849792)           0         
_________________________________________________________________
dense_11 (Dense)             (None, 10)                28497930  
=================================================================
Total params: 28,517,034
Trainable params: 28,517,034
Non-trainable params: 0

A[0]的形状是

A[0].shape = (356, 1)

Answer 1

编辑:这是我的工作代码:

from keras.models import Sequential
from keras.layers import Dense, Conv2D, Flatten
import numpy as np

A = np.zeros((1,257,356,1))     # Only for illustration
A2 = np.zeros((1,1))     # Only for illustration

model = Sequential()
model.add(Conv2D(64, kernel_size=(3,3), activation='relu', input_shape=A.shape[1:]))     # input_shape ==> (257,356,1)
model.add(Flatten())
model.add(Dense(1, activation='softmax'))

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(A, A2, validation_data = (A, A2), epochs=3)

这是 3 个时期的输出:

Train on 1 samples, validate on 1 samples
Epoch 1/3
1/1 [==============================] - 0s 250ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000
Epoch 2/3
1/1 [==============================] - 0s 141ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000
Epoch 3/3
1/1 [==============================] - 0s 156ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000

<keras.callbacks.callbacks.History at 0x1d508dbb708>