Question

我正在进行声音分类任务，我将二维声谱图数据重塑为（1，139 * 139），将其存储到列表中。有5700个这样的训练向量。当我将其提供给InceptionV3模型时，出现错误-“ 检查输入时发生错误：预期inception_v3_input具有4个维度，但数组的形状为（5700，19321）”。我不知道应该在大小或任何地方进行什么更改。请对此进行指导，以便我可以继续进行。 TIA。

代码如下： => 数据列表是包含* .wav文件中的8000个样本的列表。

specX = np.zeros([len(dataList), 19321]) # storing all the spectrogram here.
xindex = 0      
for x in dataList: 
    work = matplotlib.mlab.specgram(x)[0] #generation of spectrogram
    worka = work[0:84,0:84]      #taking square bins out of rectangular bins of 129 * 85 from each sample
    worka = scipy.misc.imresize(worka,[139,139]) #making the image size 139 * 139
    print("worka.shape : ", worka.shape)
    worka = np.reshape(worka,[1,19321]) #resizing it to fit it into the specX.
    specX[xindex,:] = worka
    xindex +=1

    #Taking 5700 samples as training data and rest is divided into test + validation
    split1 = specX.shape[0] - specX.shape[0]/20
    split1 = int(split1)
    #print("split1 : ", split1)

    split2 = (specX.shape[0] - split1) / 2
    split2 = int(split2)
    #print("split2 : ", split2)

    formatToUse = specX
    Data = np.concatenate((formatToUse,Ys),axis=1)
    DataShuffled = np.random.permutation(Data)
    newX,newY = np.hsplit(DataShuffled,[-1])
    trainX,otherX = np.split(newX,[split1])
    trainYa,otherY = np.split(newY,[split1])
    valX, testX = np.split(otherX,[split2])
    valYa,testYa = np.split(otherY,[split2])
    trainY = oneHotIt(trainYa)
    testY = oneHotIt(testYa)
    valY = oneHotIt(valYa)
    return classes,trainX,trainYa,valX,valYa,testX,testYa

现在，当我尝试将其提供给该模型时：

def googleNet(classes): 
    inception_conv = InceptionV3(include_top=False, weights='imagenet', input_shape=(139, 139, 3))
    # Freeze the layers except the last 1 layers
    for layer in inception_conv.layers[:-1]:
        layer.trainable = False

    # Check the trainable status of the individual layers
    for layer in inception_conv.layers:
        print(layer, layer.trainable)

    # Create the model
    model = models.Sequential()

    # Add the vgg convolutional base model
    model.add(inception_conv)

    # Add new layers
    model.add(layers.Flatten(input_shape=inception_conv.output_shape[1:]))
    model.add(layers.Dense(1024, activation='relu'))
    model.add(layers.Dropout(0.5))
    model.add(layers.Dense(classes, activation='softmax'))
    return model

myModel = googleNet(classes)
myModel.compile(optimizer='rmsprop', loss='categorical_crossentropy')

history = myModel.fit(np.array(trainX), np.array(trainYa),
          validation_data=(np.array(valX), np.array(valYa)),
          verbose=1,
          batch_size=batchSize,
          epochs=iterations)

预期inception_v3_input具有4个维度，但数组的形状为（5700，19321）

0 个答案: