input.py 文件源码

def read_input(image_queue):
    # Read the images and generate the decode from PNG image
    imageReader = tf.WholeFileReader()
    image_key, image_value = imageReader.read(image_queue)
    image_decode = tf.image.decode_png(image_value, channels=1)
    image_decode = tf.cast(image_decode, tf.float32)
    # Preprocess data
    image_key = rename_image_filename(image_key)    # rename image filename 
    label = search_label(image_key)
    # CREATE OBJECT
    class Record(object):
        pass
    record = Record()
    # Instantiate object
    record.key = image_key
    record.label = tf.cast(label, tf.int32)
    record.image = image_decode
    # PROCESSING IMAGES
    # reshaped_image = tf.cast(record.image, tf.float32)
    # height = 245
    # width = 320
    height = 96
    width = 96
    # Image processing for training the network. Note the many random distortions applied to the image.
    # Randomly crop a [height, width] section of the image.
    distorted_image = tf.random_crop(record.image, [height, width, 1])
    # Randomly flip the image horizontally.
    distorted_image = tf.image.random_flip_left_right(distorted_image)
    # Because these operations are not commutative, consider randomizing randomize the order their operation.
    distorted_image = tf.image.random_brightness(distorted_image, max_delta=63)
    distorted_image = tf.image.random_contrast(distorted_image, lower=0.2, upper=1.8)
    # Subtract off the mean and divide by the variance of the pixels.
    float_image = tf.image.per_image_whitening(distorted_image)
    return generate_train_batch(record.label, float_image)