data.py 文件源码

def shared_mnist():
    def shared_dataset(data_xy):
        data_x, data_y = data_xy
        np_y = np.zeros((len(data_y), 10), dtype=theano.config.floatX)
        for i in xrange(len(data_y)):
            np_y[i, data_y[i]] = 1

        shared_x = theano.shared(np.asmatrix(data_x, dtype=theano.config.floatX))
        shared_y = theano.shared(np.asmatrix(np_y, dtype=theano.config.floatX))
        return shared_x, shared_y
    f = gzip.open(curr_path + "/data/mnist.pkl.gz", "rb")
    train_set, valid_set, test_set = cPickle.load(f)
    f.close()

    test_set_x, test_set_y = shared_dataset(test_set)
    valid_set_x, valid_set_y = shared_dataset(valid_set)
    train_set_x, train_set_y = shared_dataset(train_set)

    return [train_set_x, train_set_y], [valid_set_x, valid_set_y], [test_set_x, test_set_y]