data.py

import sys
sys.path.insert(0,'../incubator-mxnet/python')

from mxnet.test_utils import download
import os.path as osp
def verified(file_path, sha1hash):
    import hashlib
    sha1 = hashlib.sha1()
    with open(file_path, 'rb') as f:
        while True:
            data = f.read(1048576)
            if not data:
                break
            sha1.update(data)
    matched = sha1.hexdigest() == sha1hash
    if not matched:
        print('Found hash mismatch in file {}, possibly due to incomplete download.'.format(file_path))
    return matched

url_format = 'https://apache-mxnet.s3-accelerate.amazonaws.com/gluon/dataset/pikachu/{}'
hashes = {'train.rec': 'e6bcb6ffba1ac04ff8a9b1115e650af56ee969c8',
          'train.idx': 'dcf7318b2602c06428b9988470c731621716c393',
          'val.rec': 'd6c33f799b4d058e82f2cb5bd9a976f69d72d520'}
for k, v in hashes.items():
    fname = 'pikachu_' + k
    target = osp.join('data', fname)
    url = url_format.format(k)
    if not osp.exists(target) or not verified(target, v):
        print('Downloading', target, url)
        download(url, fname=fname, dirname='data', overwrite=True)

import mxnet.image as image
data_shape = 256
batch_size = 32
def get_iterators(data_shape, batch_size):
    class_names = ['pikachu']
    num_class = len(class_names)
    train_iter = image.ImageDetIter(
        batch_size=batch_size,
        data_shape=(3, data_shape, data_shape),
        path_imgrec='./data/pikachu_train.rec',
        path_imgidx='./data/pikachu_train.idx',
        shuffle=True,
        mean=True,
        rand_crop=1,
        min_object_covered=0.95,
        max_attempts=200)
    val_iter = image.ImageDetIter(
        batch_size=batch_size,
        data_shape=(3, data_shape, data_shape),
        path_imgrec='./data/pikachu_val.rec',
        shuffle=False,
        mean=True)
    return train_iter, val_iter, class_names, num_class

train_data, test_data, class_names, num_class = get_iterators(data_shape, batch_size)
batch = train_data.next()
# print(batch)