How to use the redisai.Backend.tf function in redisai

def testTFGraph(self):
        _ = get_tf_graph()
        init = tf.global_variables_initializer()
        sess = tf.Session()
        sess.run(init)
        path = f'{time.time()}.pb'
        save_model(sess, path, output=['output'])
        model = load_model(path)
        os.remove(path)
        con = self.get_client()
        con.modelset(
            'tfmodel', Backend.tf, Device.cpu, model,
            input=['input'], output=['output'])
        con.tensorset('a', Tensor.scalar(DType.float, 2))
        con.modelrun('tfmodel', ['a'], 'c')
        tensor = con.tensorget('c')
        self.assertEqual([13], tensor.value)

def init(config):
    host = config['server'].split(':')[0]
    port = config['server'].split(':')[1]
    init.con = rai.Client(host=host, port=port)
    graph = raimodel.Model.load(config['modelpath'])
    inputs = ['images']
    outputs = ['output']
    init.con.modelset(
        'graph', rai.Backend.tf, rai.Device.cpu, graph,
        input=inputs, output=outputs)
    image, init.img_class = get_one_image()
    init.image = rai.BlobTensor.from_numpy(image)

import numpy as np
from redisai import Client, DType, Device, Backend
import ml2rt

client = Client()
client.tensorset('x', [2, 3], dtype=DType.float)
t = client.tensorget('x')
print(t.value)

model = ml2rt.load_model('test/testdata/graph.pb')
tensor1 = np.array([2, 3], dtype=np.float)
client.tensorset('a', tensor1)
client.tensorset('b', (12, 10), dtype=np.float)
client.modelset('m', Backend.tf,
                Device.cpu,
                inputs=['a', 'b'],
                outputs='mul',
                data=model)
client.modelrun('m', ['a', 'b'], ['mul'])
print(client.tensorget('mul'))

# Try with a script
script = ml2rt.load_script('test/testdata/script.txt')
client.scriptset('ket', Device.cpu, script)
client.scriptrun('ket', 'bar', inputs=['a', 'b'], outputs='c')