Loading a TensorFlow graph
To load a pre-trained TensorFlow graphs in MLDB, we use the tensorflow.graph
function type .
Below, we start by creating two functions. First, the fetcher
function allows us to fetch a binary blob from a remote URL. Second, the inception
function that will be used to execute the trained network and that we parameterize in the following way:
- modelFileUrl : Path to the Inception-v3 model file. The
archive
prefix and#
separator allow us to load a file inside a zip archive. (more details) - input : As input to the graph, we provide the output of the
fetch
function called with theurl
parameter. When we call it later on, the image located at the specified URL will be downloaded and passed to the graph. - output : This specifies the layer from which to return the values. The
softmax
layer is the last layer in the network so we specify that one.