I tried:
test_image = tf.convert_to_tensor(img, dtype=tf.float32)
Then following error appears:
ValueError: Tensor conversion requested dtype float32 for Tensor with dtype int64: 'Tensor("test/ArgMax:0", shape=TensorShape([Dimension(None)]), dtype=int64)'
Oops, I find the function in the API...
tf.to_float(x, name='ToFloat')