如何将图像输入 CNN 进行二元分类

Question

I am trying to create a convolutional neural network that can detect whether or not a person is having a stroke, based upon a picture of their face. The images for my dataset are contained within a directory called CNNImages , which contains two subdirectories: Strokes and RegularFaces . Each subdirectory contains jpg images that I'm trying to feed into my neural network.

Following the approach used in this tutorial , I have created the CNN, which works when fed with the MNIST dataset. However, I am having trouble feeding my own images into the neural network. I have been using the code shown by the Keras tutorial for Image data preprocessing, but it isn't working.

import tensorflow as tf
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
import numpy as np
 
dataset = tf.keras.preprocessing.image_dataset_from_directory(
    'C:\\Users\\Colin\\CNNImages',
    labels="inferred",
    label_mode="int",
    class_names=None,
    color_mode="rgb",
    batch_size=32,
    image_size=(128, 128),
    shuffle=True,
    seed=1,
    validation_split=0.2,
    subset="training",
    interpolation="bilinear",
    follow_links=False,
)

When I try to feed this dataset into my neural network using (x_train, y_train), (x_test, y_test) = dataset , I receive the following error:

ValueError: too many values to unpack (expected 2)

I've included my attempt at a neural network below.

batch_size = 128
num_classes = 2
epochs = 12

# input image dimensions
img_rows, img_cols = 128, 128

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = dataset

x_train = x_train.reshape(869,128,128,3)
x_test = x_test.reshape(217,128,128,3)

print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=(28,28,1)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

I believe I am importing the images incorrectly into the CNN, but am unsure of how to fix this. What would be the solution to getting the images to import correctly?

Edit: Below is my updated code attempt. It is unable to function, due to (x_train, y_train), (x_test, y_test) = train_ds returning ValueError: too many values to unpack (expected 2)

import tensorflow as tf
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
import numpy as np
 
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  'C:\\Users\\Colin\\Desktop\\CNNImages\\Training',
  validation_split=None,
  subset=None,
  seed=123,
  image_size=(128, 128),
  batch_size=32)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  'C:\\Users\\Colin\\Desktop\\CNNImages\\Validation',
  validation_split=None,
  subset=None,
  seed=123,
  image_size=(128, 128),
  batch_size=32)


batch_size = 128
num_classes = 2
epochs = 12

# input image dimensions
img_rows, img_cols = 128, 128

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = train_ds

x_train = x_train.reshape(869,128,128,3)
x_test = x_test.reshape(217,128,128,3)

print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=(28,28,1)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=3
)
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

Answer 1

(x_train, y_train), (x_test, y_test) = dataset part of the code raises error. Because, when you use tf.keras.preprocessing.image_dataset_from_director() , it returns batches of images, it does not split your data into train set and test set. So you need to declare seperately for train and test:

# first-approach
train_dataset = tf.keras.preprocessing.image_dataset_from_directory(train_folder, ...)
test_dataset = tf.keras.preprocessing.image_dataset_from_directory(test_folder, ...)

# second approach
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)

model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=3
)