如何在 Tensorflow 中读取 CIFAR-10 数据集？

Question

Can anyone give a clean code to load CIFAR-10 in tensoflow?

I have checked the examples given in the tensorflow's github repo. But I do not want to resize the images to 24x24 . Basically, I am looking for a easier and simpler code.

Answer 1

Please take a look at the following github page, where I have done this. If the above link fails, please follow the lead on kgeorge.github.io and look at the notebook tf_cifar.ipynb. I have attempted to load up cifar-10 data using baby steps. Please look for the function load_and_preprocess_input

The following function from that code accepts data as an np array of (nsamples, 32x32x3) float32, and labels as an np array of nsamples int32 and pre-process the data to be consumed by tensorflow training.

image_depth=3
image_height=32
image_width=32
#data = (nsamples, 32x32x3) float32
#labels = (nsamples) int32
def prepare_input(data=None, labels=None):
    global image_height, image_width, image_depth
    assert(data.shape[1] == image_height * image_width * image_depth)
    assert(data.shape[0] == labels.shape[0])
    #do mean normaization across all samples
    mu = np.mean(data, axis=0)
    mu = mu.reshape(1,-1)
    sigma = np.std(data, axis=0)
    sigma = sigma.reshape(1, -1)
    data = data - mu
    data = data / sigma
    is_nan = np.isnan(data)
    is_inf = np.isinf(data)
    if np.any(is_nan) or np.any(is_inf):
        print('data is not well-formed : is_nan {n}, is_inf: {i}'.format(n= np.any(is_nan), i=np.any(is_inf)))
    #data is transformed from (no_of_samples, 3072) to (no_of_samples , image_height, image_width, image_depth)
    #make sure the type of the data is no.float32
    data = data.reshape([-1,image_depth, image_height, image_width])
    data = data.transpose([0, 2, 3, 1])
    data = data.astype(np.float32)
    return data, labels

Answer 2

请注意，现在有一个内置函数来加载此数据集。