TensorFlow 模型训练常数损失：0.0000e+00 - 准确度：1.0000 - val_loss：0.0000e+00 - val_accuracy：1.0000

Question

我一直在尝试训练一个用于车辆图像分类的模型，但在每个训练时期我一直在损失：0.0000e+00 - 准确度：1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000。

import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
import pathlib

data_dir = tf.keras.utils.get_file('cars_photos', origin="C:\\Users\\User\\.keras\\datasets\\cars_photos")
data_dir = pathlib.Path(data_dir)

batch_size = 32
img_height = 180
img_width = 180

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

class_names = train_ds.class_names
print(class_names)

AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

num_classes = 1

model = Sequential([
  layers.experimental.preprocessing.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
  layers.Conv2D(16, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(32, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(64, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

epochs=10
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

我自己下载了图像，最小尺寸为 180x180，最大尺寸为 1920 x 1024。图像也有JPEG和一些PNG格式。

我关注image classification tutorial 并尝试寻找解决方案，但没有找到。

Answer 1

试试这个：

layers.Dense(num_classes, activation = 'sigmoid')

还有这个：

model.compile(optimizer='adam',
              loss=tf.keras.losses.BinaryCrossentropy(),
              metrics=['accuracy'])