Python data.get_dataset方法代碼示例

# 需要導入模塊: import data [as 別名]
# 或者: from data import get_dataset [as 別名]
def test_get_dataset_raw(self):
        with self.test_session():
            test_image1 = tf.constant(np.arange(4 * 4 * 3), shape=[4, 4, 3], dtype=tf.uint8)
            encoded = tf.image.encode_png(test_image1)
            image = encoded.eval()
            print(os.getcwd())
            with open(os.path.join("test_files", "test1.png"), "wb") as f:
                f.write(image)

            test_image2 = tf.constant(np.flip(np.arange(4 * 4 * 3), axis=0), shape=[4, 4, 3], dtype=tf.uint8)
            encoded = tf.image.encode_png(test_image2)
            image = encoded.eval()
            with open(os.path.join("test_files", "test2.png"), "wb") as f:
                f.write(image)

            files = glob.glob(os.path.join("test_files", "test*.png"))
            dataset = get_dataset(files)

            it = dataset.make_one_shot_iterator()
            self.assertAllClose(it.get_next(), test_image1)
            self.assertAllClose(it.get_next(), test_image2) 

# 需要導入模塊: import data [as 別名]
# 或者: from data import get_dataset [as 別名]
def load_ae(path, target_dataset, batch, all_aes, return_dataset=False):
    r_param = re.compile('(?P<name>[a-zA-Z][a-z_]*)(?P<value>(True)|(False)|(\d+(\.\d+)?(,\d+)*))')
    folders = [x for x in os.path.abspath(path).split('/') if x]
    dataset = folders[-2]
    if dataset != target_dataset:
        tf.logging.log(tf.logging.WARN,
                       'Mismatched datasets between classfier and AE (%s, %s)',
                       target_dataset, dataset)
    class_name, argpairs = folders[-1].split('_', 1)
    params = {}
    for x in r_param.findall(argpairs):
        name, value = x[:2]
        if ',' in value:
            pass
        elif value in ('True', 'False'):
            value = dict(True=True, False=False)[value]
        elif '.' in value:
            value = float(value)
        else:
            value = int(value)
        params[name] = value
    class_ = all_aes[class_name]
    dataset = data.get_dataset(dataset, dict(batch_size=batch))
    ae = class_(dataset, '/' + os.path.join(*(folders[:-2])), **params)
    if return_dataset:
        return ae, dataset
    else:
        return ae, folders[-1] 

# 需要導入模塊: import data [as 別名]
# 或者: from data import get_dataset [as 別名]
def test_get_dataset_tfrecords(self):
            with self.test_session():
                test_image1 = tf.constant(np.arange(4 * 4 * 3), shape=[4, 4, 3], dtype=tf.uint8)

                test_image2 = tf.constant(np.flip(np.arange(4 * 4 * 3), axis=0), shape=[4, 4, 3], dtype=tf.uint8)
                writer = tf.python_io.TFRecordWriter(os.path.join("test_files", "test.tfrecords"))
                testimage1_bytes_list = tf.train.BytesList(value=[test_image1.eval().tobytes()])
                example1 = tf.train.Example(
                    features=tf.train.Features(
                        feature={'data': tf.train.Feature(bytes_list=testimage1_bytes_list),
                                 'shape': tf.train.Feature(int64_list=tf.train.Int64List(value=[4, 4, 3]))}
                    )
                )
                testimage2_bytes_list = tf.train.BytesList(value=[test_image2.eval().tobytes()])
                example2 = tf.train.Example(
                    features=tf.train.Features(
                        feature={'data': tf.train.Feature(bytes_list=testimage2_bytes_list),
                                 'shape': tf.train.Feature(int64_list=tf.train.Int64List(value=[4, 4, 3]))}
                    )
                )
                writer.write(example1.SerializeToString())
                writer.write(example2.SerializeToString())
                writer.close()

                files = glob.glob(os.path.join("test_files", "*.tfrecords"))
                dataset = get_dataset(files)
                it = dataset.make_one_shot_iterator()
                self.assertAllClose(it.get_next(), test_image1)
                self.assertAllClose(it.get_next(), test_image2) 

# 需要導入模塊: import data [as 別名]
# 或者: from data import get_dataset [as 別名]
def test_preprocess_dataset_batch2_float_raw(self):
        with self.test_session():
            test_image1 = tf.constant(np.arange(4 * 4 * 3), shape=[4, 4, 3], dtype=tf.uint8)

            test_image2 = tf.constant(np.flip(np.arange(4 * 4 * 3), axis=0), shape=[4, 4, 3], dtype=tf.uint8)
            writer = tf.python_io.TFRecordWriter(os.path.join("test_files", "test.tfrecords"))
            testimage1_bytes_list = tf.train.BytesList(value=[test_image1.eval().tobytes()])
            example1 = tf.train.Example(
                features=tf.train.Features(
                    feature={'data': tf.train.Feature(bytes_list=testimage1_bytes_list),
                             'shape': tf.train.Feature(int64_list=tf.train.Int64List(value=[4, 4, 3]))}
                )
            )
            testimage2_bytes_list = tf.train.BytesList(value=[test_image2.eval().tobytes()])
            example2 = tf.train.Example(
                features=tf.train.Features(
                    feature={'data': tf.train.Feature(bytes_list=testimage2_bytes_list),
                             'shape': tf.train.Feature(int64_list=tf.train.Int64List(value=[4, 4, 3]))}
                )
            )
            writer.write(example1.SerializeToString())
            writer.write(example2.SerializeToString())
            writer.close()
            files = glob.glob(os.path.join("test_files", "*.tfrecords"))
            dataset = get_dataset(files)

            dataset = preprocess_dataset(dataset, size=[64, 64], batch_size=2,
                                         float_pixels=True)

            it = dataset.make_one_shot_iterator()
            data = it.get_next().eval()
            self.assertEqual(data.shape, (2, 64, 64, 3))
            self.assertAllClose(max(data.flatten()), max(test_image1.eval().flatten()) / 127.5 - 1.)
            self.assertAllClose(min(data.flatten()), min(test_image1.eval().flatten()) / 127.5 - 1.) 

# 需要導入模塊: import data [as 別名]
# 或者: from data import get_dataset [as 別名]
def test_preprocess_dataset_batch2_float_tfrecord(self):
        with self.test_session():
            test_image1 = tf.constant(np.arange(4 * 4 * 3) * 5, shape=[4, 4, 3], dtype=tf.uint8)
            encoded = tf.image.encode_png(test_image1)
            image1 = encoded.eval()
            with open(os.path.join("test_files", "test1.png"), "wb") as f:
                f.write(image1)

            test_image2 = tf.constant(np.flip(np.arange(4 * 4 * 3) * 5, axis=0), shape=[4, 4, 3],
                                      dtype=tf.uint8)
            encoded = tf.image.encode_png(test_image2)
            image2 = encoded.eval()
            with open(os.path.join("test_files", "test2.png"), "wb") as f:
                f.write(image2)

            files = glob.glob(os.path.join("test_files", "test*.png"))
            dataset = get_dataset(files)

            dataset = preprocess_dataset(dataset, size=[64, 64], batch_size=2,
                                         float_pixels=True)

            it = dataset.make_one_shot_iterator()
            data = it.get_next().eval()
            self.assertEqual(data.shape, (2, 64, 64, 3))
            self.assertAllClose(max(data.flatten()), max(test_image1.eval().flatten()) / 127.5 - 1.)
            self.assertAllClose(min(data.flatten()), min(test_image1.eval().flatten()) / 127.5 - 1.) 

# 需要導入模塊: import data [as 別名]
# 或者: from data import get_dataset [as 別名]
def build_data_iterator(hps, files, current_res_h, current_res_w, batch_size=None, label_list=None,
                        num_shards=None, shard_index=None):
    random.shuffle(files)
    dataset = get_dataset(files, current_res_h, current_res_w, hps.epochs_per_res, batch_size,
                          label_list=label_list, num_shards=None, shard_index=None)
    it = dataset.make_one_shot_iterator()
    return it 

# 需要導入模塊: import data [as 別名]
# 或者: from data import get_dataset [as 別名]
def get_dt(filename, dataset):
    dt = pd.read_csv(filename)
    _, _, _, y_test = data.get_dataset(dataset)
    pd_y_test = pd.DataFrame({'TrueIndex': y_test.argmax(1)})
    return preprocess_summary_file(dt, pd_y_test)