Keras 精度不变
Keras accuracy does not change
我有几千个音频文件，我想使用 Keras 和 Theano 对它们进行分类。到目前为止，我生成了每个音频文件的 28x28 频谱图（越大可能越好，但我只是想让算法在这一点上工作）并将图像读入矩阵。所以最后我得到了这个大图像矩阵来输入网络进行图像分类。
在一个教程中我找到了这个 mnist 分类代码：
import numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense
from keras.utils import np_utils
batch_size = 128
nb_classes = 10
nb_epochs = 2
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255
print(X_train.shape[0], "train samples")
print(X_test.shape[0], "test samples")
y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(Dense(output_dim = 100, input_dim = 784, activation= "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = nb_classes, activation = "softmax"))
model.compile(optimizer = "adam", loss = "categorical_crossentropy")
model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epochs, show_accuracy = True, verbose = 2, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 0)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])
这段代码 运行s，我得到了预期的结果：
(60000L, 'train samples')
(10000L, 'test samples')
Train on 60000 samples, validate on 10000 samples
Epoch 1/2
2s - loss: 0.2988 - acc: 0.9131 - val_loss: 0.1314 - val_acc: 0.9607
Epoch 2/2
2s - loss: 0.1144 - acc: 0.9651 - val_loss: 0.0995 - val_acc: 0.9673
('Test score: ', 0.099454972004890438)
('Test accuracy: ', 0.96730000000000005)
到目前为止，一切 运行 都很完美，但是当我将上述算法应用到我的数据集时，准确性会卡住。
我的代码如下：
import os
import pandas as pd
from sklearn.cross_validation import train_test_split
from keras.models import Sequential
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.utils import np_utils
import AudioProcessing as ap
import ImageTools as it
batch_size = 128
nb_classes = 2
nb_epoch = 10
for i in range(20):
print "\n"
# Generate spectrograms if necessary
if(len(os.listdir("./AudioNormalPathalogicClassification/Image")) > 0):
print "Audio files are already processed. Skipping..."
else:
print "Generating spectrograms for the audio files..."
ap.audio_2_image("./AudioNormalPathalogicClassification/Audio/","./AudioNormalPathalogicClassification/Image/",".wav",".png",(28,28))
# Read the result csv
df = pd.read_csv('./AudioNormalPathalogicClassification/Result/result.csv', header = None)
df.columns = ["RegionName","IsNormal"]
bool_mapping = {True : 1, False : 0}
nb_classes = 2
for col in df:
if(col == "RegionName"):
a = 3
else:
df[col] = df[col].map(bool_mapping)
y = df.iloc[:,1:].values
y = np_utils.to_categorical(y, nb_classes)
# Load images into memory
print "Loading images into memory..."
X = it.load_images("./AudioNormalPathalogicClassification/Image/",".png")
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 0)
X_train = X_train.reshape(X_train.shape[0], 784)
X_test = X_test.reshape(X_test.shape[0], 784)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255
print("X_train shape: " + str(X_train.shape))
print(str(X_train.shape[0]) + " train samples")
print(str(X_test.shape[0]) + " test samples")
model = Sequential()
model.add(Dense(output_dim = 100, input_dim = 784, activation= "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = nb_classes, activation = "softmax"))
model.compile(loss = "categorical_crossentropy", optimizer = "adam")
print model.summary()
model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy = True, verbose = 1, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 1)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])
AudioProcessing.py
import os
import scipy as sp
import scipy.io.wavfile as wav
import matplotlib.pylab as pylab
import Image
def save_spectrogram_scipy(source_filename, destination_filename, size):
dt = 0.0005
NFFT = 1024
Fs = int(1.0/dt)
fs, audio = wav.read(source_filename)
if(len(audio.shape) >= 2):
audio = sp.mean(audio, axis = 1)
fig = pylab.figure()
ax = pylab.Axes(fig, [0,0,1,1])
ax.set_axis_off()
fig.add_axes(ax)
pylab.specgram(audio, NFFT = NFFT, Fs = Fs, noverlap = 900, cmap="gray")
pylab.savefig(destination_filename)
img = Image.open(destination_filename).convert("L")
img = img.resize(size)
img.save(destination_filename)
pylab.clf()
del img
def audio_2_image(source_directory, destination_directory, audio_extension, image_extension, size):
nb_files = len(os.listdir(source_directory));
count = 0
for file in os.listdir(source_directory):
if file.endswith(audio_extension):
destinationName = file[:-4]
save_spectrogram_scipy(source_directory + file, destination_directory + destinationName + image_extension, size)
count += 1
print ("Generating spectrogram for files " + str(count) + " / " + str(nb_files) + ".")
ImageTools.py
import os
import numpy as np
import matplotlib.image as mpimg
def load_images(source_directory, image_extension):
image_matrix = []
nb_files = len(os.listdir(source_directory));
count = 0
for file in os.listdir(source_directory):
if file.endswith(image_extension):
with open(source_directory + file,"r+b") as f:
img = mpimg.imread(f)
img = img.flatten()
image_matrix.append(img)
del img
count += 1
#print ("File " + str(count) + " / " + str(nb_files) + " loaded.")
return np.asarray(image_matrix)
所以我运行上面的代码并收到：
Audio files are already processed. Skipping...
Loading images into memory...
X_train shape: (2394L, 784L)
2394 train samples
1027 test samples
--------------------------------------------------------------------------------
Initial input shape: (None, 784)
--------------------------------------------------------------------------------
Layer (name) Output Shape Param #
--------------------------------------------------------------------------------
Dense (dense) (None, 100) 78500
Dense (dense) (None, 200) 20200
Dense (dense) (None, 200) 40200
Dense (dense) (None, 2) 402
--------------------------------------------------------------------------------
Total params: 139302
--------------------------------------------------------------------------------
None
Train on 2394 samples, validate on 1027 samples
Epoch 1/10
2394/2394 [==============================] - 0s - loss: 0.6898 - acc: 0.5455 - val_loss: 0.6835 - val_acc: 0.5716
Epoch 2/10
2394/2394 [==============================] - 0s - loss: 0.6879 - acc: 0.5522 - val_loss: 0.6901 - val_acc: 0.5716
Epoch 3/10
2394/2394 [==============================] - 0s - loss: 0.6880 - acc: 0.5522 - val_loss: 0.6842 - val_acc: 0.5716
Epoch 4/10
2394/2394 [==============================] - 0s - loss: 0.6883 - acc: 0.5522 - val_loss: 0.6829 - val_acc: 0.5716
Epoch 5/10
2394/2394 [==============================] - 0s - loss: 0.6885 - acc: 0.5522 - val_loss: 0.6836 - val_acc: 0.5716
Epoch 6/10
2394/2394 [==============================] - 0s - loss: 0.6887 - acc: 0.5522 - val_loss: 0.6832 - val_acc: 0.5716
Epoch 7/10
2394/2394 [==============================] - 0s - loss: 0.6882 - acc: 0.5522 - val_loss: 0.6859 - val_acc: 0.5716
Epoch 8/10
2394/2394 [==============================] - 0s - loss: 0.6882 - acc: 0.5522 - val_loss: 0.6849 - val_acc: 0.5716
Epoch 9/10
2394/2394 [==============================] - 0s - loss: 0.6885 - acc: 0.5522 - val_loss: 0.6836 - val_acc: 0.5716
Epoch 10/10
2394/2394 [==============================] - 0s - loss: 0.6877 - acc: 0.5522 - val_loss: 0.6849 - val_acc: 0.5716
1027/1027 [==============================] - 0s
('Test score: ', 0.68490593621422047)
('Test accuracy: ', 0.57156767283349563)
我尝试更改网络，添加更多的 epoch，但无论如何我总是得到相同的结果。我不明白为什么我会得到相同的结果。
如有任何帮助，我们将不胜感激。谢谢。
编辑：
我发现了一个像素值没有被正确读取的错误。我将下面的 ImageTools.py 固定为：
import os
import numpy as np
from scipy.misc import imread
def load_images(source_directory, image_extension):
image_matrix = []
nb_files = len(os.listdir(source_directory));
count = 0
for file in os.listdir(source_directory):
if file.endswith(image_extension):
with open(source_directory + file,"r+b") as f:
img = imread(f)
img = img.flatten()
image_matrix.append(img)
del img
count += 1
#print ("File " + str(count) + " / " + str(nb_files) + " loaded.")
return np.asarray(image_matrix)
现在我实际上得到了从 0 到 255 的灰度像素值，所以现在我将它除以 255 是有意义的。但是，我仍然得到相同的结果。
最可能的原因是优化器不适合您的数据集。这是文档中 Keras optimizers 的列表。
我建议您先尝试使用默认参数值的 SGD。如果仍然不起作用，请将学习率除以 10。如有必要，请多做几次。如果你的学习率到了1e-6还是不行，那就是你又出问题了
总而言之，替换这一行：
model.compile(loss = "categorical_crossentropy", optimizer = "adam")
有了这个：
from keras.optimizers import SGD
opt = SGD(lr=0.01)
model.compile(loss = "categorical_crossentropy", optimizer = opt)
再改几次学习率不行的话
如果这是问题所在，您应该会看到损失在几个 epoch 后变得更低。
经过一番检查，我发现问题出在数据本身。它非常脏，因为在同一个输入中有 2 个不同的输出，因此造成了混乱。清理数据后，现在我的准确率上升到 %69。仍然不够好，但至少我现在可以在数据清晰的情况下从这里开始工作。
我用下面的代码来测试：
import os
import sys
import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.utils import np_utils
sys.path.append("./")
import AudioProcessing as ap
import ImageTools as it
# input image dimensions
img_rows, img_cols = 28, 28
dim = 1
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
nb_pool = 2
# convolution kernel size
nb_conv = 3
batch_size = 128
nb_classes = 2
nb_epoch = 200
for i in range(20):
print "\n"
## Generate spectrograms if necessary
if(len(os.listdir("./AudioNormalPathalogicClassification/Image")) > 0):
print "Audio files are already processed. Skipping..."
else:
# Read the result csv
df = pd.read_csv('./AudioNormalPathalogicClassification/Result/AudioNormalPathalogicClassification_result.csv', header = None, encoding = "utf-8")
df.columns = ["RegionName","Filepath","IsNormal"]
bool_mapping = {True : 1, False : 0}
for col in df:
if(col == "RegionName" or col == "Filepath"):
a = 3
else:
df[col] = df[col].map(bool_mapping)
region_names = df.iloc[:,0].values
filepaths = df.iloc[:,1].values
y = df.iloc[:,2].values
#Generate spectrograms and make a new CSV file
print "Generating spectrograms for the audio files..."
result = ap.audio_2_image(filepaths, region_names, y, "./AudioNormalPathalogicClassification/Image/", ".png",(img_rows,img_cols))
df = pd.DataFrame(data = result)
df.to_csv("NormalVsPathalogic.csv",header= False, index = False, encoding = "utf-8")
# Load images into memory
print "Loading images into memory..."
df = pd.read_csv('NormalVsPathalogic.csv', header = None, encoding = "utf-8")
y = df.iloc[:,0].values
y = np_utils.to_categorical(y, nb_classes)
y = np.asarray(y)
X = df.iloc[:,1:].values
X = np.asarray(X)
X = X.reshape(X.shape[0], dim, img_rows, img_cols)
X = X.astype("float32")
X /= 255
print X.shape
model = Sequential()
model.add(Convolution2D(64, nb_conv, nb_conv,
border_mode='valid',
input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))
model.add(Convolution2D(32, nb_conv, nb_conv))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adadelta')
print model.summary()
model.fit(X, y, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy = True, verbose = 1)
看看这个
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile( loss = "categorical_crossentropy",
optimizer = sgd,
metrics=['accuracy']
)
我在 MNIST 上取得了更好的结果
如果精度没有变化，则意味着优化器已找到损失的局部最小值。这可能是一个不受欢迎的最小值。一种常见的局部最小值是始终预测具有最多数据点的 class。您应该在 classes 上使用加权以避免这个最小值。
from sklearn.utils import compute_class_weight
classWeight = compute_class_weight('balanced', outputLabels, outputs)
classWeight = dict(enumerate(classWeight))
model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epochs, show_accuracy = True, verbose = 2, validation_data = (X_test, y_test), class_weight=classWeight)
我遇到了类似的问题。在 Keras 中使用 nputils 对目标变量进行 One-hot 编码，解决了准确性和验证损失被卡住的问题。使用权重来平衡目标 类 进一步提高了性能。
解法：
from keras.utils.np.utils import to_categorical
y_train = to_categorical(y_train)
y_val = to_categorical(y_val)
我和你有同样的问题
我的解决方案是循环而不是历元
for i in range(10):
history = model.fit_generator(generator=training_generator,
validation_data=validation_generator,
use_multiprocessing=True,
workers=6,
epochs=1)
你也可以在每个时期保存模型，这样你就可以在你想要的任何时期后暂停训练
for i in range(10):
history = model.fit_generator(generator=training_generator,
validation_data=validation_generator,
use_multiprocessing=True,
workers=6,
epochs=1)
#save model
model.save('drive/My Drive/vggnet10epochs.h5')
model = load_model('drive/My Drive/vggnet10epochs.h5')
另一个我在这里没有提到的解决方案，但对我造成了类似的问题是最后一个神经元的激活函数，特别是如果它是 relu 而不是像 [=15= 这样的非线性的东西].
换句话说，它可能会帮助你在最后一层使用非线性激活函数
最后一层：
model.add(keras.layers.Dense(1, activation='relu'))
输出：
7996/7996 [==============================] - 1s 76us/sample - loss: 6.3474 - accuracy: 0.5860
Epoch 2/30
7996/7996 [==============================] - 0s 58us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 3/30
7996/7996 [==============================] - 0s 58us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 4/30
7996/7996 [==============================] - 0s 57us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 5/30
7996/7996 [==============================] - 0s 58us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 6/30
7996/7996 [==============================] - 0s 60us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 7/30
7996/7996 [==============================] - 0s 57us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 8/30
7996/7996 [==============================] - 0s 57us/sample - loss: 6.3473 - accuracy: 0.5860
现在我使用了非线性激活函数：
model.add(keras.layers.Dense(1, activation='sigmoid'))
输出：
7996/7996 [==============================] - 1s 74us/sample - loss: 0.7663 - accuracy: 0.5899
Epoch 2/30
7996/7996 [==============================] - 0s 59us/sample - loss: 0.6243 - accuracy: 0.5860
Epoch 3/30
7996/7996 [==============================] - 0s 56us/sample - loss: 0.5399 - accuracy: 0.7580
Epoch 4/30
7996/7996 [==============================] - 0s 56us/sample - loss: 0.4694 - accuracy: 0.7905
Epoch 5/30
7996/7996 [==============================] - 0s 57us/sample - loss: 0.4363 - accuracy: 0.8040
Epoch 6/30
7996/7996 [==============================] - 0s 60us/sample - loss: 0.4139 - accuracy: 0.8099
Epoch 7/30
7996/7996 [==============================] - 0s 58us/sample - loss: 0.3967 - accuracy: 0.8228
Epoch 8/30
7996/7996 [==============================] - 0s 61us/sample - loss: 0.3826 - accuracy: 0.8260
这不是原始答案的直接解决方案，但由于搜索此问题时Google上的答案是#1，它可能会对某些人有所帮助。
我有类似的问题。我有一个二进制 class 标记为 1 和 2。在测试了不同种类的优化器和激活函数后，我发现问题的根源是我标记为 classes。换句话说，我将标签更改为 0 和 1 而不是 1 和 2，然后这个问题就解决了！
我使用此 'sigmoid' 激活获得了 13% 的准确度增量
model = Sequential()
model.add(Dense(3072, input_shape=(3072,), activation="sigmoid"))
model.add(Dense(512, activation="sigmoid"))
model.add(Dense(1, activation="sigmoid"))
或者您也可以测试以下内容，其中 'relu' 在第一层和隐藏层中。
model = Sequential()
model.add(Dense(3072, input_shape=(3072,), activation="relu"))
model.add(Dense(512, activation="sigmoid"))
model.add(Dense(1, activation="sigmoid"))
我错误地在末尾添加了一个 softmax 而不是 sigmoid。尝试做后者。当我这样做时，它按预期工作。对于一个输出层，softmax 总是给出 1 的值，这就是发生的情况。
我在 multi-class 遇到了同样的问题，尝试更改默认优化器 Adam 将其更改为 sgd。
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
您也可以尝试不同的激活函数，例如。 （relu、sigmoid、softmax、softplus 等）
一些 imp 链接
正如其他人所指出的，优化器可能不适合您的 data/model，它陷入了局部最小值。神经网络至少应该能够过度拟合数据（training_acc 接近 1）。
我曾经遇到过类似的问题。我通过尝试不同的优化器解决了问题（在我的例子中是从 SGD 到 RMSprop）
如上所述，问题主要出在所选择的优化器类型上。然而，它也可以由顶层 2 个具有相同激活函数（例如 softmax）的密集层这一事实驱动。
在这种情况下，NN 找到局部最小值并且无法从该点下降更多，围绕相同的 acc (val_acc) 值滚动。
希望对大家有所帮助。
我知道这是一个老问题，但截至今天（14/06/2021），@theTechGuy 的评论在 tf 2.3 上运行良好。代码是：
from tensorflow.keras.optimizers import SGD
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile( loss = "categorical_crossentropy",
optimizer = sgd,
metrics=['accuracy']
)
就我而言，我的问题是二进制的，我使用的是 'softmax' 激活函数，但它不起作用。我更改为 'sigmoid' 它对我来说正常工作。
我尝试了很多优化器和激活函数，但唯一有用的是 Batchnormalization1。我想这也是一个很好的做法。
您可以将其导入为：
from tensorflow.keras.layers import BatchNormalization
并简单地在每个隐藏层之前添加它：
model.add(BatchNormalization())
我遇到了同样的问题，但就我而言，这是由我的数据中的 non-regularized 列引起的。这个专栏有巨大的价值。修复为我解决了它。
所以，我只是将它转换为 0 和 1 左右的值。
我遇到了完全相同的问题：验证损失和准确性在各个时期保持不变。我将批量大小增加了 10 倍，将学习率降低了 100 倍，等等。它没有用。
受单语和 Ranjab 回答的启发，我的最后一次尝试奏效了。
我的解决方案是添加 Batchnormalization 并按如下方式排列顺序：
Conv - DropOut - BatchNorm - Activation - Pool。
按照 中的建议。
我有几千个音频文件，我想使用 Keras 和 Theano 对它们进行分类。到目前为止，我生成了每个音频文件的 28x28 频谱图（越大可能越好，但我只是想让算法在这一点上工作）并将图像读入矩阵。所以最后我得到了这个大图像矩阵来输入网络进行图像分类。
在一个教程中我找到了这个 mnist 分类代码：
import numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense
from keras.utils import np_utils
batch_size = 128
nb_classes = 10
nb_epochs = 2
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255
print(X_train.shape[0], "train samples")
print(X_test.shape[0], "test samples")
y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(Dense(output_dim = 100, input_dim = 784, activation= "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = nb_classes, activation = "softmax"))
model.compile(optimizer = "adam", loss = "categorical_crossentropy")
model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epochs, show_accuracy = True, verbose = 2, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 0)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])
这段代码 运行s，我得到了预期的结果：
(60000L, 'train samples')
(10000L, 'test samples')
Train on 60000 samples, validate on 10000 samples
Epoch 1/2
2s - loss: 0.2988 - acc: 0.9131 - val_loss: 0.1314 - val_acc: 0.9607
Epoch 2/2
2s - loss: 0.1144 - acc: 0.9651 - val_loss: 0.0995 - val_acc: 0.9673
('Test score: ', 0.099454972004890438)
('Test accuracy: ', 0.96730000000000005)
到目前为止，一切 运行 都很完美，但是当我将上述算法应用到我的数据集时，准确性会卡住。
我的代码如下：
import os
import pandas as pd
from sklearn.cross_validation import train_test_split
from keras.models import Sequential
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.utils import np_utils
import AudioProcessing as ap
import ImageTools as it
batch_size = 128
nb_classes = 2
nb_epoch = 10
for i in range(20):
print "\n"
# Generate spectrograms if necessary
if(len(os.listdir("./AudioNormalPathalogicClassification/Image")) > 0):
print "Audio files are already processed. Skipping..."
else:
print "Generating spectrograms for the audio files..."
ap.audio_2_image("./AudioNormalPathalogicClassification/Audio/","./AudioNormalPathalogicClassification/Image/",".wav",".png",(28,28))
# Read the result csv
df = pd.read_csv('./AudioNormalPathalogicClassification/Result/result.csv', header = None)
df.columns = ["RegionName","IsNormal"]
bool_mapping = {True : 1, False : 0}
nb_classes = 2
for col in df:
if(col == "RegionName"):
a = 3
else:
df[col] = df[col].map(bool_mapping)
y = df.iloc[:,1:].values
y = np_utils.to_categorical(y, nb_classes)
# Load images into memory
print "Loading images into memory..."
X = it.load_images("./AudioNormalPathalogicClassification/Image/",".png")
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 0)
X_train = X_train.reshape(X_train.shape[0], 784)
X_test = X_test.reshape(X_test.shape[0], 784)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255
print("X_train shape: " + str(X_train.shape))
print(str(X_train.shape[0]) + " train samples")
print(str(X_test.shape[0]) + " test samples")
model = Sequential()
model.add(Dense(output_dim = 100, input_dim = 784, activation= "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = nb_classes, activation = "softmax"))
model.compile(loss = "categorical_crossentropy", optimizer = "adam")
print model.summary()
model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy = True, verbose = 1, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 1)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])
AudioProcessing.py
import os
import scipy as sp
import scipy.io.wavfile as wav
import matplotlib.pylab as pylab
import Image
def save_spectrogram_scipy(source_filename, destination_filename, size):
dt = 0.0005
NFFT = 1024
Fs = int(1.0/dt)
fs, audio = wav.read(source_filename)
if(len(audio.shape) >= 2):
audio = sp.mean(audio, axis = 1)
fig = pylab.figure()
ax = pylab.Axes(fig, [0,0,1,1])
ax.set_axis_off()
fig.add_axes(ax)
pylab.specgram(audio, NFFT = NFFT, Fs = Fs, noverlap = 900, cmap="gray")
pylab.savefig(destination_filename)
img = Image.open(destination_filename).convert("L")
img = img.resize(size)
img.save(destination_filename)
pylab.clf()
del img
def audio_2_image(source_directory, destination_directory, audio_extension, image_extension, size):
nb_files = len(os.listdir(source_directory));
count = 0
for file in os.listdir(source_directory):
if file.endswith(audio_extension):
destinationName = file[:-4]
save_spectrogram_scipy(source_directory + file, destination_directory + destinationName + image_extension, size)
count += 1
print ("Generating spectrogram for files " + str(count) + " / " + str(nb_files) + ".")
ImageTools.py
import os
import numpy as np
import matplotlib.image as mpimg
def load_images(source_directory, image_extension):
image_matrix = []
nb_files = len(os.listdir(source_directory));
count = 0
for file in os.listdir(source_directory):
if file.endswith(image_extension):
with open(source_directory + file,"r+b") as f:
img = mpimg.imread(f)
img = img.flatten()
image_matrix.append(img)
del img
count += 1
#print ("File " + str(count) + " / " + str(nb_files) + " loaded.")
return np.asarray(image_matrix)
所以我运行上面的代码并收到：
Audio files are already processed. Skipping...
Loading images into memory...
X_train shape: (2394L, 784L)
2394 train samples
1027 test samples
--------------------------------------------------------------------------------
Initial input shape: (None, 784)
--------------------------------------------------------------------------------
Layer (name) Output Shape Param #
--------------------------------------------------------------------------------
Dense (dense) (None, 100) 78500
Dense (dense) (None, 200) 20200
Dense (dense) (None, 200) 40200
Dense (dense) (None, 2) 402
--------------------------------------------------------------------------------
Total params: 139302
--------------------------------------------------------------------------------
None
Train on 2394 samples, validate on 1027 samples
Epoch 1/10
2394/2394 [==============================] - 0s - loss: 0.6898 - acc: 0.5455 - val_loss: 0.6835 - val_acc: 0.5716
Epoch 2/10
2394/2394 [==============================] - 0s - loss: 0.6879 - acc: 0.5522 - val_loss: 0.6901 - val_acc: 0.5716
Epoch 3/10
2394/2394 [==============================] - 0s - loss: 0.6880 - acc: 0.5522 - val_loss: 0.6842 - val_acc: 0.5716
Epoch 4/10
2394/2394 [==============================] - 0s - loss: 0.6883 - acc: 0.5522 - val_loss: 0.6829 - val_acc: 0.5716
Epoch 5/10
2394/2394 [==============================] - 0s - loss: 0.6885 - acc: 0.5522 - val_loss: 0.6836 - val_acc: 0.5716
Epoch 6/10
2394/2394 [==============================] - 0s - loss: 0.6887 - acc: 0.5522 - val_loss: 0.6832 - val_acc: 0.5716
Epoch 7/10
2394/2394 [==============================] - 0s - loss: 0.6882 - acc: 0.5522 - val_loss: 0.6859 - val_acc: 0.5716
Epoch 8/10
2394/2394 [==============================] - 0s - loss: 0.6882 - acc: 0.5522 - val_loss: 0.6849 - val_acc: 0.5716
Epoch 9/10
2394/2394 [==============================] - 0s - loss: 0.6885 - acc: 0.5522 - val_loss: 0.6836 - val_acc: 0.5716
Epoch 10/10
2394/2394 [==============================] - 0s - loss: 0.6877 - acc: 0.5522 - val_loss: 0.6849 - val_acc: 0.5716
1027/1027 [==============================] - 0s
('Test score: ', 0.68490593621422047)
('Test accuracy: ', 0.57156767283349563)
我尝试更改网络，添加更多的 epoch，但无论如何我总是得到相同的结果。我不明白为什么我会得到相同的结果。
如有任何帮助，我们将不胜感激。谢谢。
编辑： 我发现了一个像素值没有被正确读取的错误。我将下面的 ImageTools.py 固定为：
import os
import numpy as np
from scipy.misc import imread
def load_images(source_directory, image_extension):
image_matrix = []
nb_files = len(os.listdir(source_directory));
count = 0
for file in os.listdir(source_directory):
if file.endswith(image_extension):
with open(source_directory + file,"r+b") as f:
img = imread(f)
img = img.flatten()
image_matrix.append(img)
del img
count += 1
#print ("File " + str(count) + " / " + str(nb_files) + " loaded.")
return np.asarray(image_matrix)
现在我实际上得到了从 0 到 255 的灰度像素值，所以现在我将它除以 255 是有意义的。但是，我仍然得到相同的结果。
最可能的原因是优化器不适合您的数据集。这是文档中 Keras optimizers 的列表。
我建议您先尝试使用默认参数值的 SGD。如果仍然不起作用，请将学习率除以 10。如有必要，请多做几次。如果你的学习率到了1e-6还是不行，那就是你又出问题了
总而言之，替换这一行：
model.compile(loss = "categorical_crossentropy", optimizer = "adam")
有了这个：
from keras.optimizers import SGD
opt = SGD(lr=0.01)
model.compile(loss = "categorical_crossentropy", optimizer = opt)
再改几次学习率不行的话
如果这是问题所在，您应该会看到损失在几个 epoch 后变得更低。
经过一番检查，我发现问题出在数据本身。它非常脏，因为在同一个输入中有 2 个不同的输出，因此造成了混乱。清理数据后，现在我的准确率上升到 %69。仍然不够好，但至少我现在可以在数据清晰的情况下从这里开始工作。
我用下面的代码来测试：
import os
import sys
import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.utils import np_utils
sys.path.append("./")
import AudioProcessing as ap
import ImageTools as it
# input image dimensions
img_rows, img_cols = 28, 28
dim = 1
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
nb_pool = 2
# convolution kernel size
nb_conv = 3
batch_size = 128
nb_classes = 2
nb_epoch = 200
for i in range(20):
print "\n"
## Generate spectrograms if necessary
if(len(os.listdir("./AudioNormalPathalogicClassification/Image")) > 0):
print "Audio files are already processed. Skipping..."
else:
# Read the result csv
df = pd.read_csv('./AudioNormalPathalogicClassification/Result/AudioNormalPathalogicClassification_result.csv', header = None, encoding = "utf-8")
df.columns = ["RegionName","Filepath","IsNormal"]
bool_mapping = {True : 1, False : 0}
for col in df:
if(col == "RegionName" or col == "Filepath"):
a = 3
else:
df[col] = df[col].map(bool_mapping)
region_names = df.iloc[:,0].values
filepaths = df.iloc[:,1].values
y = df.iloc[:,2].values
#Generate spectrograms and make a new CSV file
print "Generating spectrograms for the audio files..."
result = ap.audio_2_image(filepaths, region_names, y, "./AudioNormalPathalogicClassification/Image/", ".png",(img_rows,img_cols))
df = pd.DataFrame(data = result)
df.to_csv("NormalVsPathalogic.csv",header= False, index = False, encoding = "utf-8")
# Load images into memory
print "Loading images into memory..."
df = pd.read_csv('NormalVsPathalogic.csv', header = None, encoding = "utf-8")
y = df.iloc[:,0].values
y = np_utils.to_categorical(y, nb_classes)
y = np.asarray(y)
X = df.iloc[:,1:].values
X = np.asarray(X)
X = X.reshape(X.shape[0], dim, img_rows, img_cols)
X = X.astype("float32")
X /= 255
print X.shape
model = Sequential()
model.add(Convolution2D(64, nb_conv, nb_conv,
border_mode='valid',
input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))
model.add(Convolution2D(32, nb_conv, nb_conv))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adadelta')
print model.summary()
model.fit(X, y, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy = True, verbose = 1)
看看这个
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile( loss = "categorical_crossentropy",
optimizer = sgd,
metrics=['accuracy']
)
我在 MNIST 上取得了更好的结果
如果精度没有变化，则意味着优化器已找到损失的局部最小值。这可能是一个不受欢迎的最小值。一种常见的局部最小值是始终预测具有最多数据点的 class。您应该在 classes 上使用加权以避免这个最小值。
from sklearn.utils import compute_class_weight
classWeight = compute_class_weight('balanced', outputLabels, outputs)
classWeight = dict(enumerate(classWeight))
model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epochs, show_accuracy = True, verbose = 2, validation_data = (X_test, y_test), class_weight=classWeight)
我遇到了类似的问题。在 Keras 中使用 nputils 对目标变量进行 One-hot 编码，解决了准确性和验证损失被卡住的问题。使用权重来平衡目标 类 进一步提高了性能。
解法：
from keras.utils.np.utils import to_categorical
y_train = to_categorical(y_train)
y_val = to_categorical(y_val)
我和你有同样的问题 我的解决方案是循环而不是历元
for i in range(10):
history = model.fit_generator(generator=training_generator,
validation_data=validation_generator,
use_multiprocessing=True,
workers=6,
epochs=1)
for i in range(10):
history = model.fit_generator(generator=training_generator,
validation_data=validation_generator,
use_multiprocessing=True,
workers=6,
epochs=1)
#save model
model.save('drive/My Drive/vggnet10epochs.h5')
model = load_model('drive/My Drive/vggnet10epochs.h5')
另一个我在这里没有提到的解决方案，但对我造成了类似的问题是最后一个神经元的激活函数，特别是如果它是 relu 而不是像 [=15= 这样的非线性的东西].
换句话说，它可能会帮助你在最后一层使用非线性激活函数
最后一层：
model.add(keras.layers.Dense(1, activation='relu'))
输出：
7996/7996 [==============================] - 1s 76us/sample - loss: 6.3474 - accuracy: 0.5860
Epoch 2/30
7996/7996 [==============================] - 0s 58us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 3/30
7996/7996 [==============================] - 0s 58us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 4/30
7996/7996 [==============================] - 0s 57us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 5/30
7996/7996 [==============================] - 0s 58us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 6/30
7996/7996 [==============================] - 0s 60us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 7/30
7996/7996 [==============================] - 0s 57us/sample - loss: 6.3473 - accuracy: 0.5860
Epoch 8/30
7996/7996 [==============================] - 0s 57us/sample - loss: 6.3473 - accuracy: 0.5860
现在我使用了非线性激活函数：
model.add(keras.layers.Dense(1, activation='sigmoid'))
输出：
7996/7996 [==============================] - 1s 74us/sample - loss: 0.7663 - accuracy: 0.5899
Epoch 2/30
7996/7996 [==============================] - 0s 59us/sample - loss: 0.6243 - accuracy: 0.5860
Epoch 3/30
7996/7996 [==============================] - 0s 56us/sample - loss: 0.5399 - accuracy: 0.7580
Epoch 4/30
7996/7996 [==============================] - 0s 56us/sample - loss: 0.4694 - accuracy: 0.7905
Epoch 5/30
7996/7996 [==============================] - 0s 57us/sample - loss: 0.4363 - accuracy: 0.8040
Epoch 6/30
7996/7996 [==============================] - 0s 60us/sample - loss: 0.4139 - accuracy: 0.8099
Epoch 7/30
7996/7996 [==============================] - 0s 58us/sample - loss: 0.3967 - accuracy: 0.8228
Epoch 8/30
7996/7996 [==============================] - 0s 61us/sample - loss: 0.3826 - accuracy: 0.8260
这不是原始答案的直接解决方案，但由于搜索此问题时Google上的答案是#1，它可能会对某些人有所帮助。
我有类似的问题。我有一个二进制 class 标记为 1 和 2。在测试了不同种类的优化器和激活函数后，我发现问题的根源是我标记为 classes。换句话说，我将标签更改为 0 和 1 而不是 1 和 2，然后这个问题就解决了！
我使用此 'sigmoid' 激活获得了 13% 的准确度增量
model = Sequential()
model.add(Dense(3072, input_shape=(3072,), activation="sigmoid"))
model.add(Dense(512, activation="sigmoid"))
model.add(Dense(1, activation="sigmoid"))
或者您也可以测试以下内容，其中 'relu' 在第一层和隐藏层中。
model = Sequential()
model.add(Dense(3072, input_shape=(3072,), activation="relu"))
model.add(Dense(512, activation="sigmoid"))
model.add(Dense(1, activation="sigmoid"))
我错误地在末尾添加了一个 softmax 而不是 sigmoid。尝试做后者。当我这样做时，它按预期工作。对于一个输出层，softmax 总是给出 1 的值，这就是发生的情况。
我在 multi-class 遇到了同样的问题，尝试更改默认优化器 Adam 将其更改为 sgd。
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
您也可以尝试不同的激活函数，例如。 （relu、sigmoid、softmax、softplus 等）
一些 imp 链接
正如其他人所指出的，优化器可能不适合您的 data/model，它陷入了局部最小值。神经网络至少应该能够过度拟合数据（training_acc 接近 1）。 我曾经遇到过类似的问题。我通过尝试不同的优化器解决了问题（在我的例子中是从 SGD 到 RMSprop）
如上所述，问题主要出在所选择的优化器类型上。然而，它也可以由顶层 2 个具有相同激活函数（例如 softmax）的密集层这一事实驱动。 在这种情况下，NN 找到局部最小值并且无法从该点下降更多，围绕相同的 acc (val_acc) 值滚动。 希望对大家有所帮助。
我知道这是一个老问题，但截至今天（14/06/2021），@theTechGuy 的评论在 tf 2.3 上运行良好。代码是：
from tensorflow.keras.optimizers import SGD
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile( loss = "categorical_crossentropy",
optimizer = sgd,
metrics=['accuracy']
)
就我而言，我的问题是二进制的，我使用的是 'softmax' 激活函数，但它不起作用。我更改为 'sigmoid' 它对我来说正常工作。
我尝试了很多优化器和激活函数，但唯一有用的是 Batchnormalization1。我想这也是一个很好的做法。 您可以将其导入为：
from tensorflow.keras.layers import BatchNormalization
并简单地在每个隐藏层之前添加它：
model.add(BatchNormalization())
我遇到了同样的问题，但就我而言，这是由我的数据中的 non-regularized 列引起的。这个专栏有巨大的价值。修复为我解决了它。
所以，我只是将它转换为 0 和 1 左右的值。
我遇到了完全相同的问题：验证损失和准确性在各个时期保持不变。我将批量大小增加了 10 倍，将学习率降低了 100 倍，等等。它没有用。
受单语和 Ranjab 回答的启发，我的最后一次尝试奏效了。
我的解决方案是添加 Batchnormalization 并按如下方式排列顺序：
Conv - DropOut - BatchNorm - Activation - Pool。
按照