Tensorflow 使用TF Keras ImageDataGenerator时，预测返回相同的值

我正在使用

猫狗数据集

来训练使用

Tensorflow Keras

的模型，并使用

ImageDataGenerator.flow_从_目录

读取文件

训练和验证的准确性是不错的，但当尝试对测试数据进行预测时，模型预测的是所有图像的同一类别

培训代码如下所示：

import os, shutil
import tensorflow as tf
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dropout, Dense
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.losses import binary_crossentropy
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import numpy as np
import matplotlib.pyplot as plt

# Path to Training Directory
train_dir = 'Dogs_Vs_Cats_Small/train'

# Path to Validation Directory
validation_dir = 'Dogs_Vs_Cats_Small/validation'

#### Create the Convolutional Base

Max_Pool_Size = (2,2)
model = Sequential([
    Conv2D(input_shape = (150, 150, 3), filters = 32, kernel_size = (3,3), activation = 'relu', 
           padding = 'valid', data_format = 'channels_last'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size)
])


#### Define the Dense Layers on Top of Convolutional Base

model.add(Flatten())
model.add(Dense(units = 512, activation = 'relu'))
model.add(Dense(units = 1, activation = 'sigmoid'))
model.summary()

model.compile(optimizer = RMSprop(learning_rate = 0.001), loss = 'binary_crossentropy', metrics = 'acc')

Train_Gen = ImageDataGenerator(1./255)
Val_Gen = ImageDataGenerator(1./255)

Train_Generator = Train_Gen.flow_from_directory(train_dir, target_size = (150,150), batch_size = 20,
                                               class_mode = 'binary')

Val_Generator = Val_Gen.flow_from_directory(validation_dir, target_size = (150, 150), class_mode = 'binary',
                                           batch_size = 20)

batch_size = 20
target_size = (150,150)
No_Of_Training_Images = Train_Generator.classes.shape[0]
No_Of_Val_Images = Val_Generator.classes.shape[0]
steps_per_epoch = No_Of_Training_Images/batch_size
validation_steps = No_Of_Val_Images/batch_size

history = model.fit(x = Train_Generator, shuffle=True, epochs = 20, 
          steps_per_epoch = steps_per_epoch,
          validation_data = Val_Generator
          , validation_steps = validation_steps
         )

Test_Dir = 'Dogs_Vs_Cats_Very_Small/test'

Test_Generator = ImageDataGenerator(1./255).flow_from_directory(Test_Dir, 
           target_size = (150,150), batch_size = 1, 
           shuffle = False, class_mode = 'binary') # This outputs Found 17 images belonging to 2 classes.

No_Of_Samples = len(Test_Generator.filenames)

testPredictions = model.predict(Test_Generator, steps = No_Of_Samples)


predictedClassIndices=np.argmax(testPredictions,axis=1)
print(predictedClassIndices)

filenames = Test_Generator.filenames
for f in range(len(filenames)):
    print(filenames[f],":",predictedClassIndices[f])

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])


cats/cat.1546.jpg : 0
cats/cat.1547.jpg : 0
cats/cat.1548.jpg : 0
cats/cat.1549.jpg : 0
cats/cat.1550.jpg : 0
cats/cat.1566.jpg : 0
cats/cat.1593.jpg : 0
cats/cat.1594.jpg : 0
dogs/dog.1514.jpg : 0
dogs/dog.1520.jpg : 0
dogs/dog.1525.jpg : 0
dogs/dog.1551.jpg : 0
dogs/dog.1555.jpg : 0
dogs/dog.1574.jpg : 0
dogs/dog.1594.jpg : 0
dogs/dog.1597.jpg : 0
dogs/dog.1599.jpg : 0

[[1.0473319e-05]
 [9.8473930e-01]
 [2.9069009e-01]
 [5.0639841e-07]
 [1.8511847e-01]
 [6.0166395e-01]
 [4.2568660e-01]
 [4.6028453e-01]
 [7.8800195e-01]
 [8.5675471e-02]
 [8.2654454e-02]
 [7.2898394e-01]
 [1.5504999e-01]
 [8.2106847e-01]
 [8.7003058e-01]
 [9.9999285e-01]
 [5.1210046e-01]]

现在，我对

测试数据
进行预测，如下所示：

import os, shutil
import tensorflow as tf
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dropout, Dense
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.losses import binary_crossentropy
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import numpy as np
import matplotlib.pyplot as plt

# Path to Training Directory
train_dir = 'Dogs_Vs_Cats_Small/train'

# Path to Validation Directory
validation_dir = 'Dogs_Vs_Cats_Small/validation'

#### Create the Convolutional Base

Max_Pool_Size = (2,2)
model = Sequential([
    Conv2D(input_shape = (150, 150, 3), filters = 32, kernel_size = (3,3), activation = 'relu', 
           padding = 'valid', data_format = 'channels_last'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size)
])


#### Define the Dense Layers on Top of Convolutional Base

model.add(Flatten())
model.add(Dense(units = 512, activation = 'relu'))
model.add(Dense(units = 1, activation = 'sigmoid'))
model.summary()

model.compile(optimizer = RMSprop(learning_rate = 0.001), loss = 'binary_crossentropy', metrics = 'acc')

Train_Gen = ImageDataGenerator(1./255)
Val_Gen = ImageDataGenerator(1./255)

Train_Generator = Train_Gen.flow_from_directory(train_dir, target_size = (150,150), batch_size = 20,
                                               class_mode = 'binary')

Val_Generator = Val_Gen.flow_from_directory(validation_dir, target_size = (150, 150), class_mode = 'binary',
                                           batch_size = 20)

batch_size = 20
target_size = (150,150)
No_Of_Training_Images = Train_Generator.classes.shape[0]
No_Of_Val_Images = Val_Generator.classes.shape[0]
steps_per_epoch = No_Of_Training_Images/batch_size
validation_steps = No_Of_Val_Images/batch_size

history = model.fit(x = Train_Generator, shuffle=True, epochs = 20, 
          steps_per_epoch = steps_per_epoch,
          validation_data = Val_Generator
          , validation_steps = validation_steps
         )

Test_Dir = 'Dogs_Vs_Cats_Very_Small/test'

Test_Generator = ImageDataGenerator(1./255).flow_from_directory(Test_Dir, 
           target_size = (150,150), batch_size = 1, 
           shuffle = False, class_mode = 'binary') # This outputs Found 17 images belonging to 2 classes.

No_Of_Samples = len(Test_Generator.filenames)

testPredictions = model.predict(Test_Generator, steps = No_Of_Samples)


predictedClassIndices=np.argmax(testPredictions,axis=1)
print(predictedClassIndices)

filenames = Test_Generator.filenames
for f in range(len(filenames)):
    print(filenames[f],":",predictedClassIndices[f])

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])


cats/cat.1546.jpg : 0
cats/cat.1547.jpg : 0
cats/cat.1548.jpg : 0
cats/cat.1549.jpg : 0
cats/cat.1550.jpg : 0
cats/cat.1566.jpg : 0
cats/cat.1593.jpg : 0
cats/cat.1594.jpg : 0
dogs/dog.1514.jpg : 0
dogs/dog.1520.jpg : 0
dogs/dog.1525.jpg : 0
dogs/dog.1551.jpg : 0
dogs/dog.1555.jpg : 0
dogs/dog.1574.jpg : 0
dogs/dog.1594.jpg : 0
dogs/dog.1597.jpg : 0
dogs/dog.1599.jpg : 0

[[1.0473319e-05]
 [9.8473930e-01]
 [2.9069009e-01]
 [5.0639841e-07]
 [1.8511847e-01]
 [6.0166395e-01]
 [4.2568660e-01]
 [4.6028453e-01]
 [7.8800195e-01]
 [8.5675471e-02]
 [8.2654454e-02]
 [7.2898394e-01]
 [1.5504999e-01]
 [8.2106847e-01]
 [8.7003058e-01]
 [9.9999285e-01]
 [5.1210046e-01]]

上述
Print
语句的输出，即
预测类
如下所示：

import os, shutil
import tensorflow as tf
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dropout, Dense
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.losses import binary_crossentropy
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import numpy as np
import matplotlib.pyplot as plt

# Path to Training Directory
train_dir = 'Dogs_Vs_Cats_Small/train'

# Path to Validation Directory
validation_dir = 'Dogs_Vs_Cats_Small/validation'

#### Create the Convolutional Base

Max_Pool_Size = (2,2)
model = Sequential([
    Conv2D(input_shape = (150, 150, 3), filters = 32, kernel_size = (3,3), activation = 'relu', 
           padding = 'valid', data_format = 'channels_last'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size)
])


#### Define the Dense Layers on Top of Convolutional Base

model.add(Flatten())
model.add(Dense(units = 512, activation = 'relu'))
model.add(Dense(units = 1, activation = 'sigmoid'))
model.summary()

model.compile(optimizer = RMSprop(learning_rate = 0.001), loss = 'binary_crossentropy', metrics = 'acc')

Train_Gen = ImageDataGenerator(1./255)
Val_Gen = ImageDataGenerator(1./255)

Train_Generator = Train_Gen.flow_from_directory(train_dir, target_size = (150,150), batch_size = 20,
                                               class_mode = 'binary')

Val_Generator = Val_Gen.flow_from_directory(validation_dir, target_size = (150, 150), class_mode = 'binary',
                                           batch_size = 20)

batch_size = 20
target_size = (150,150)
No_Of_Training_Images = Train_Generator.classes.shape[0]
No_Of_Val_Images = Val_Generator.classes.shape[0]
steps_per_epoch = No_Of_Training_Images/batch_size
validation_steps = No_Of_Val_Images/batch_size

history = model.fit(x = Train_Generator, shuffle=True, epochs = 20, 
          steps_per_epoch = steps_per_epoch,
          validation_data = Val_Generator
          , validation_steps = validation_steps
         )

Test_Dir = 'Dogs_Vs_Cats_Very_Small/test'

Test_Generator = ImageDataGenerator(1./255).flow_from_directory(Test_Dir, 
           target_size = (150,150), batch_size = 1, 
           shuffle = False, class_mode = 'binary') # This outputs Found 17 images belonging to 2 classes.

No_Of_Samples = len(Test_Generator.filenames)

testPredictions = model.predict(Test_Generator, steps = No_Of_Samples)


predictedClassIndices=np.argmax(testPredictions,axis=1)
print(predictedClassIndices)

filenames = Test_Generator.filenames
for f in range(len(filenames)):
    print(filenames[f],":",predictedClassIndices[f])

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])


cats/cat.1546.jpg : 0
cats/cat.1547.jpg : 0
cats/cat.1548.jpg : 0
cats/cat.1549.jpg : 0
cats/cat.1550.jpg : 0
cats/cat.1566.jpg : 0
cats/cat.1593.jpg : 0
cats/cat.1594.jpg : 0
dogs/dog.1514.jpg : 0
dogs/dog.1520.jpg : 0
dogs/dog.1525.jpg : 0
dogs/dog.1551.jpg : 0
dogs/dog.1555.jpg : 0
dogs/dog.1574.jpg : 0
dogs/dog.1594.jpg : 0
dogs/dog.1597.jpg : 0
dogs/dog.1599.jpg : 0

[[1.0473319e-05]
 [9.8473930e-01]
 [2.9069009e-01]
 [5.0639841e-07]
 [1.8511847e-01]
 [6.0166395e-01]
 [4.2568660e-01]
 [4.6028453e-01]
 [7.8800195e-01]
 [8.5675471e-02]
 [8.2654454e-02]
 [7.2898394e-01]
 [1.5504999e-01]
 [8.2106847e-01]
 [8.7003058e-01]
 [9.9999285e-01]
 [5.1210046e-01]]

如上所述，所有图像都预测为
Class=0
，即
Cats

我已经研究过了，我的数据是平衡的（1000张猫的图片和1000张狗的图片），所以，根据我的理解，重新平衡我的数据集或调整类权重并不适用。我也尝试过“增加训练时间”

编辑：测试预测的内容如下所示：

import os, shutil
import tensorflow as tf
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dropout, Dense
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.losses import binary_crossentropy
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import numpy as np
import matplotlib.pyplot as plt

# Path to Training Directory
train_dir = 'Dogs_Vs_Cats_Small/train'

# Path to Validation Directory
validation_dir = 'Dogs_Vs_Cats_Small/validation'

#### Create the Convolutional Base

Max_Pool_Size = (2,2)
model = Sequential([
    Conv2D(input_shape = (150, 150, 3), filters = 32, kernel_size = (3,3), activation = 'relu', 
           padding = 'valid', data_format = 'channels_last'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size),
    Conv2D(filters = 128, kernel_size = (3,3), activation = 'relu', padding = 'valid'),
    MaxPooling2D(pool_size = Max_Pool_Size)
])


#### Define the Dense Layers on Top of Convolutional Base

model.add(Flatten())
model.add(Dense(units = 512, activation = 'relu'))
model.add(Dense(units = 1, activation = 'sigmoid'))
model.summary()

model.compile(optimizer = RMSprop(learning_rate = 0.001), loss = 'binary_crossentropy', metrics = 'acc')

Train_Gen = ImageDataGenerator(1./255)
Val_Gen = ImageDataGenerator(1./255)

Train_Generator = Train_Gen.flow_from_directory(train_dir, target_size = (150,150), batch_size = 20,
                                               class_mode = 'binary')

Val_Generator = Val_Gen.flow_from_directory(validation_dir, target_size = (150, 150), class_mode = 'binary',
                                           batch_size = 20)

batch_size = 20
target_size = (150,150)
No_Of_Training_Images = Train_Generator.classes.shape[0]
No_Of_Val_Images = Val_Generator.classes.shape[0]
steps_per_epoch = No_Of_Training_Images/batch_size
validation_steps = No_Of_Val_Images/batch_size

history = model.fit(x = Train_Generator, shuffle=True, epochs = 20, 
          steps_per_epoch = steps_per_epoch,
          validation_data = Val_Generator
          , validation_steps = validation_steps
         )

Test_Dir = 'Dogs_Vs_Cats_Very_Small/test'

Test_Generator = ImageDataGenerator(1./255).flow_from_directory(Test_Dir, 
           target_size = (150,150), batch_size = 1, 
           shuffle = False, class_mode = 'binary') # This outputs Found 17 images belonging to 2 classes.

No_Of_Samples = len(Test_Generator.filenames)

testPredictions = model.predict(Test_Generator, steps = No_Of_Samples)


predictedClassIndices=np.argmax(testPredictions,axis=1)
print(predictedClassIndices)

filenames = Test_Generator.filenames
for f in range(len(filenames)):
    print(filenames[f],":",predictedClassIndices[f])

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])


cats/cat.1546.jpg : 0
cats/cat.1547.jpg : 0
cats/cat.1548.jpg : 0
cats/cat.1549.jpg : 0
cats/cat.1550.jpg : 0
cats/cat.1566.jpg : 0
cats/cat.1593.jpg : 0
cats/cat.1594.jpg : 0
dogs/dog.1514.jpg : 0
dogs/dog.1520.jpg : 0
dogs/dog.1525.jpg : 0
dogs/dog.1551.jpg : 0
dogs/dog.1555.jpg : 0
dogs/dog.1574.jpg : 0
dogs/dog.1594.jpg : 0
dogs/dog.1597.jpg : 0
dogs/dog.1599.jpg : 0

[[1.0473319e-05]
 [9.8473930e-01]
 [2.9069009e-01]
 [5.0639841e-07]
 [1.8511847e-01]
 [6.0166395e-01]
 [4.2568660e-01]
 [4.6028453e-01]
 [7.8800195e-01]
 [8.5675471e-02]
 [8.2654454e-02]
 [7.2898394e-01]
 [1.5504999e-01]
 [8.2106847e-01]
 [8.7003058e-01]
 [9.9999285e-01]
 [5.1210046e-01]]

有人能帮我纠正一下吗

提前感谢大家。
当您将类分配给
testPredictions
结果时，这里的问题在最后一步。
argmax
方法“返回沿轴的最大值索引”。在您的情况下，它总是
0
，因为沿着
axis=1
只有一个元素（索引
0
）

由于您正在进行二进制分类，并且类是平衡的，因此应用0.5概率阈值来分配类是最有意义的：

predictedClassIndices = testPredictions > 0.5

for idx, filename in enumerate(filenames):
    print(filename,":",predictedClassIndices[idx])

你能为你的例子提供
testPredictions
的内容吗？@Lukasz-Tracewski，当然，谢谢你的回答。我已经用
testPredictions
的内容更新了我的问题。