图像分类器

Question

我使用Python中的张量流库制作了一个图像分类器。有人可以帮助我提高准确性并减少验证损失吗？我总共使用了 849 张图像进行训练和验证。有7个班级。运行 50 个 epoch 后，损失：0.2181 - 准确度：0.9132 - val_loss：1.2094 - val_accuracy：0.6982。有没有办法提高 val 准确性并减少 val 损失。

from google.colab import drive

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

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

data_dir = 'drive/MyDrive/Data_Set_2/Data_Set'

batch_size = 16
img_height = 180
img_width = 180

train_ds = tf.keras.utils.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.utils.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)

for image_batch, labels_batch in train_ds:
  print(image_batch.shape)
  print(labels_batch.shape)
  break

AUTOTUNE = tf.data.AUTOTUNE

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

normalization_layer = layers.Rescaling(1./255)

normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(normalized_ds))
first_image = image_batch[0]
print(np.min(first_image), np.max(first_image))

num_classes = len(class_names)

data_augmentation = keras.Sequential(
  [
    layers.RandomFlip("horizontal",
                      input_shape=(img_height,
                                  img_width,
                                  3)),
    layers.RandomRotation(0.1),
    layers.RandomZoom(0.1),
  ]
)

num_classes = len(class_names)

model = Sequential([
  data_augmentation,
  layers.Rescaling(1./255),
  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.Dropout(0.5),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes, name="outputs")
])

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

model.summary()

epochs = 50
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

model.save('Image_Classsification.keras')

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

我希望验证精度至少为 0.8。非常感谢您的帮助。

Answer 1

1.生成更多数据：您还可以尝试使用 GAN 进行数据增强。
2.增加纪元
3.迁移学习使用这个link