Load TensorFlow model from memory
up vote
0
down vote
favorite
Im am running TensorFlow inference in Java and I want to load the model from memory (since I already have it in memory).
Right now I am using the SavedModelBundle.load() method (https://www.tensorflow.org/api_docs/java/reference/org/tensorflow/SavedModelBundle.html#load(java.lang.String,%20java.lang.String...)) that requires the model to be on disk in an exportDir.
Is there a functionality to read the model from memory (InputStream or byte)?
I am using TensorFlow for Java 1.8.0 but I can use the latest stable. Also a solution with Python is feasible.
Thanks.
java python tensorflow
add a comment |
up vote
0
down vote
favorite
Im am running TensorFlow inference in Java and I want to load the model from memory (since I already have it in memory).
Right now I am using the SavedModelBundle.load() method (https://www.tensorflow.org/api_docs/java/reference/org/tensorflow/SavedModelBundle.html#load(java.lang.String,%20java.lang.String...)) that requires the model to be on disk in an exportDir.
Is there a functionality to read the model from memory (InputStream or byte)?
I am using TensorFlow for Java 1.8.0 but I can use the latest stable. Also a solution with Python is feasible.
Thanks.
java python tensorflow
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
Im am running TensorFlow inference in Java and I want to load the model from memory (since I already have it in memory).
Right now I am using the SavedModelBundle.load() method (https://www.tensorflow.org/api_docs/java/reference/org/tensorflow/SavedModelBundle.html#load(java.lang.String,%20java.lang.String...)) that requires the model to be on disk in an exportDir.
Is there a functionality to read the model from memory (InputStream or byte)?
I am using TensorFlow for Java 1.8.0 but I can use the latest stable. Also a solution with Python is feasible.
Thanks.
java python tensorflow
Im am running TensorFlow inference in Java and I want to load the model from memory (since I already have it in memory).
Right now I am using the SavedModelBundle.load() method (https://www.tensorflow.org/api_docs/java/reference/org/tensorflow/SavedModelBundle.html#load(java.lang.String,%20java.lang.String...)) that requires the model to be on disk in an exportDir.
Is there a functionality to read the model from memory (InputStream or byte)?
I am using TensorFlow for Java 1.8.0 but I can use the latest stable. Also a solution with Python is feasible.
Thanks.
java python tensorflow
java python tensorflow
asked Nov 13 at 9:20
alex
12
12
add a comment |
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53277602%2fload-tensorflow-model-from-memory%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown