tensorflow - 如何为 tensorflow 准备我自己的数据？

Question

我在 ubuntu 14.04 上安装了 Tensorflow。我已完成 MNIST For ML Beginners教程。我明白了。

也不，我尝试使用我自己的数据。我的训练数据为 T[1000][10]。标签是 L[2]、1 或 0。

我如何访问我的数据 mnist.train.images ?

Answer 1

在 input_data.py 中，这两个函数完成了主要工作。

1.下载

def maybe_download(filename, work_directory):
    """Download the data from Yann's website, unless it's already here."""
    if not os.path.exists(work_directory):
        os.mkdir(work_directory)
    filepath = os.path.join(work_directory, filename)
    if not os.path.exists(filepath):
        filepath, _ = urlretrieve(SOURCE_URL + filename, filepath)
        statinfo = os.stat(filepath)
        print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
    return filepath

2 图像到 nparray

def extract_images(filename):
    """Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
    print('Extracting', filename)
    with gzip.open(filename) as bytestream:
        magic = _read32(bytestream)
        if magic != 2051:
            raise ValueError(
                'Invalid magic number %d in MNIST image file: %s' %
                (magic, filename))
        num_images = _read32(bytestream)
        rows = _read32(bytestream)
        cols = _read32(bytestream)
        buf = bytestream.read(rows * cols * num_images)
        data = numpy.frombuffer(buf, dtype=numpy.uint8)
        data = data.reshape(num_images, rows, cols, 1)
        return data

根据您的数据集和位置，您可以调用:

local_file = maybe_download(TRAIN_IMAGES, train_dir)
train_images = extract_images(local_file)

查看完整源代码 https://github.com/nlintz/TensorFlow-Tutorials/blob/master/input_data.py .