Question

我正在尝试使用tensorflow中的tf.train.shuffle_batch函数，然后我需要先使用tf.image.decode_jpeg（或其他类似函数加载png和jpg）加载图像。但我发现图像是作为概率图加载的，这意味着像素值的最大值为1，像素值的最小值为0.以下是我从github repo更新的代码。我不知道为什么像素值被归一化为[0,1]，我也找不到有关张量流的相关文档。谁能帮助我？谢谢。

def load_examples(self, input_dir,  flip, scale_size, batch_size, min_queue_examples):
    input_paths = get_image_paths(input_dir)
    with tf.name_scope("load_images"):
        path_queue = tf.train.string_input_producer(input_paths)
        reader = tf.WholeFileReader()
        paths, contents = reader.read(path_queue)
        # note this is important for truncated images
        raw_input = tf.image.decode_jpeg(contents,try_recover_truncated = True, acceptable_fraction=0.5)
        raw_input = tf.image.convert_image_dtype(raw_input, dtype=tf.float32)
        raw_input.set_shape([None, None, 3])

        # break apart image pair and move to range [-1, 1]
        width = tf.shape(raw_input)[1]  # [height, width, channels]
        a_images = preprocess(raw_input[:, :width // 2, :])
        b_images = raw_input[:, width // 2:, :]

    inputs, targets = [a_images, b_images]

    def transform(image):
        r = image

        r = tf.image.resize_images(r, [self.image_height, self.image_width], method=tf.image.ResizeMethod.AREA)
        return r
    def transform_gaze(image):
        r = image
        r = tf.image.resize_images(r, [self.gaze_height, self.gaze_width], method=tf.image.ResizeMethod.AREA)
        return r
    with tf.name_scope("input_images"):
        input_images = transform(inputs)

    with tf.name_scope("target_images"):
        target_images = transform(targets)
    total_image_count = len(input_paths)
    # target_images = tf.image.per_image_standardization(target_images)
    target_images = target_images[:,:,0]
    target_images = tf.expand_dims(target_images, 2)
    inputs_batch, targets_batch = tf.train.shuffle_batch([input_images, target_images],
                                         batch_size=batch_size,
                                         num_threads=1,
                                         capacity=min_queue_examples + 3 * batch_size,
                                         min_after_dequeue=min_queue_examples)
    # inputs_batch, targets_batch = tf.train.batch([input_images, target_images],batch_size=batch_size)
    return inputs_batch, targets_batch, total_image_count

Answer 1

值为[0,1]因为tf.image.decode_*方法的作用。

通常，当方法返回浮点张量时，其值应该在[0,1]范围内，而如果返回的张量是uint8，则值应该在[0,255]范围内。

此外，当您使用tf.image.convert_image_dtype方法转换输入图片的dtype时，您将应用该转化规则。

如果输入图像是uint8图像并将其转换为float32，则值将在[0,1]范围内缩放。如果您的图像已经是浮点数，则其值应该在该范围内，并且不执行任何操作。

图像像素值是否为tf.image.decode_jpeg和tf.train.shuffle_batch标准化？

1 个答案: