Tensorflow：从 TFRecords 文件中提取图像和标签

Question

我有一个 TFRecords 文件，其中包含带有标签、名称、大小等的图像。我的目标是将标签和图像提取为 numpy 数组。

我执行以下操作来加载文件：

def extract_fn(data_record):
    features = {
        # Extract features using the keys set during creation
        "image/class/label":    tf.FixedLenFeature([], tf.int64),
        "image/encoded":        tf.VarLenFeature(tf.string),
    }
    sample = tf.parse_single_example(data_record, features)
    #sample = tf.cast(sample["image/encoded"], tf.float32)
    return sample

filename = "path\train-00-of-10"
dataset = tf.data.TFRecordDataset(filename)
dataset = dataset.map(extract_fn)
iterator = dataset.make_one_shot_iterator()
next_element = iterator.get_next()

with tf.Session() as sess:
    while True:
        data_record = sess.run(next_element)
        print(data_record)

图片保存为字符串。如何将图像转换为 float32？我试过 sample = tf.cast(sample["image/encoded"], tf.float32) 没有用。我希望 data_record 成为一个列表，其中包含作为 numpy 数组的图像和作为 np.int32 数字的标签。我该怎么做？

现在 data_record 看起来像这样：

{'image/encoded': SparseTensorValue(indices=array([[0]]), values=array([b'\xff\xd8\ ... 8G\xff\xd9'], dtype=object), dense_shape=array([1])), 'image/class/label': 394}

我不知道如何处理它。我将不胜感激任何帮助

编辑

如果我在 extract_fn() 中打印 sample 和 sample['image/encoded']，我会得到以下结果：

print(sample) = {'image/encoded': <tensorflow.python.framework.sparse_tensor.SparseTensor object at 0x7fe41ec15978>, 'image/class/label': <tf.Tensor 'ParseSingleExample/ParseSingleExample:3' shape=() dtype=int64>}

print(sample['image/encoded'] = SparseTensor(indices=Tensor("ParseSingleExample/ParseSingleExample:0", shape=(?, 1), dtype=int64), values=Tensor("ParseSingleExample/ParseSingleExample:1", shape=(?,), dtype=string), dense_shape=Tensor("ParseSingleExample/ParseSingleExample:2", shape=(1,), dtype=int64))

好像图像是稀疏张量，tf.image.decode_image报错。将图像提取为 tf.float32 张量的正确方法是什么？

Answer 1

我相信您存储的图像编码为 JPEG 或 PNG 或其他格式。所以，在阅读的时候，你必须解码它们：

def extract_fn(data_record):
    features = {
        # Extract features using the keys set during creation
        "image/class/label":    tf.FixedLenFeature([], tf.int64),
        "image/encoded":        tf.VarLenFeature(tf.string),
    }
    sample = tf.parse_single_example(data_record, features)
    image = tf.image.decode_image(sample['image/encoded'], dtype=tf.float32) 
    label = sample['image/class/label']
    return image, label

...

with tf.Session() as sess:
    while True:
        image, label = sess.run(next_element)
        image = image.reshape(IMAGE_SHAPE)

更新： 似乎您将数据作为稀疏张量中的单个单元格值获取。尝试将其转换回密集并在解码前后进行检查：

def extract_fn(data_record):
    features = {
        # Extract features using the keys set during creation
        "image/class/label":    tf.FixedLenFeature([], tf.int64),
        "image/encoded":        tf.VarLenFeature(tf.string),
    }
    sample = tf.parse_single_example(data_record, features)
    label = sample['image/class/label']
    dense = tf.sparse_tensor_to_dense(sample['image/encoded'])

    # Comment it if you got an error and inspect just dense:
    image = tf.image.decode_image(dense, dtype=tf.float32) 

    return dense, image, label

Answer 2

如果我没看错，你只需要 numpy.fromstring

img_str = (example.features.feature['image_raw'].bytes_list.value)
image = np.fromstring(img_str, dtype=np.float32)

或者如果你需要tensorflow函数，你需要在你的parse函数中添加tf.decode_raw，我认为最好将图像和标签分开

def extract_fn(data_record):
    features = {
        # Extract features using the keys set during creation
        "image/class/label":    tf.FixedLenFeature([], tf.int64),
        "image/encoded":        tf.VarLenFeature(tf.string),
    }
    sample = tf.parse_single_example(data_record, features)
    image = tf.decode_raw(sample['image/encoded'], tf.float32)
    label = sample['image/class/label']

    return image, label

Tensorflow：从 TFRecords 文件中提取图像和标签

Tensorflow: Extracting image and label from TFRecords file

python

tensorflow

tensorflow-datasets