Python Tensorflow数据被分为1类

你好，飞越者

我目前正在努力解决代码中的一个错误。 当我运行代码时，出于某种原因，它将训练图像分类到一个类中，这违背了代码的目的。我似乎找不到它这样做的原因。你能帮帮我吗？

这可能是新手犯的错误，对此我深表歉意

这是我的密码：

from tensorflow import keras
import pandas as pd
from keras.models import load_model
from keras.utils import CustomObjectScope
from keras.initializers import glorot_uniform
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import numpy as np

line = "__________________________________"




data_x = os.path.join('/tmp/MyData/car-or-no-car/car')


data_y = os.path.join('/tmp/MyData/car-or-no-car/no-car')

print('Total training x images:', len(os.listdir(data_x)))
print('Total training y images:', len(os.listdir(data_y)))



class myCallback(tf.keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if(logs.get('acc')>0.9999):
      print("Accuracy has reached 99.99 percent so cancelling training!")
      self.model.stop_training = True



train_datagen = ImageDataGenerator(rescale=1/255)


train_generator = train_datagen.flow_from_directory(
        '/tmp/MyData/car-or-no-car',  # This is the source directory for training images
        target_size=(300, 300),  # All images will be resized to 150x150
        batch_size=128,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

callbacks = myCallback()


model = tf.keras.models.Sequential([

    tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(300, 300, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])




from tensorflow.keras.optimizers import RMSprop

model.compile(loss='binary_crossentropy',
              optimizer=RMSprop(lr=0.001),
              metrics=['acc'])




train_datagen = ImageDataGenerator(rescale=1/255)

train_generator = train_datagen.flow_from_directory(
        '/tmp/MyData/',  # This is the source directory for training images
        target_size=(300, 300),  # All images will be resized to 150x150
        batch_size=128,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

history = model.fit_generator(
      train_generator,
      steps_per_epoch=8,  
      epochs=10,
      verbose=1)

print(line)
model.save('testing.h5')
print("The Model has been Saved!")
print(line)