Questions tagged [serving]

93 questions
2
votes
1 answer

serving polymer bundles conditionally

What are the options for service polymer es6-bundle,es5-bundle and unbundled versions conditionally ? preferred option would be nginx if that's possible, so basically how to detect HTTP2 and if there's good regex for user agent to detect es6
MySqlError
  • 620
  • 8
  • 20
2
votes
0 answers

bazel-bin/tensorflow_serving/example/inception_client

Traceback (most recent call last): File "/root/serving/bazel-bin/tensorflow_serving/example/inception_client.runfiles/tf_serving/tensorflow_serving/example/inception_client.py", line 56, in tf.app.run() File…
2
votes
0 answers

Start serving file while converting it [PHP]

i'm wondering how to serve a file while i'm converting it, to lower thhe waiting time of the client. I'v tried the chunked header in php, but only the first bytes of the file are downloaded. header('Transfer-Encoding: chunked'); …
Ininity83
  • 21
  • 1
2
votes
1 answer

Trying to dynamically set Pages in Loop with Node.js

I'm trying to do something (which I hope) is simple: receive JSON from the a database and loop through it to create all the necessary page routes in Node.js. As of now, I'm just using stubbed data, but the console.log is always showing the last…
streetlight
  • 5,968
  • 13
  • 62
  • 101
2
votes
1 answer

serving images? htaccess redirect the images folder?

i have a php script that uploads an image, renames it to a random hash, creates folders based on the hash, stores the original image in the last created folder, and finally, creates 2 other thumbnails for it... regular image...…
Kenny
  • 675
  • 1
  • 7
  • 20
1
vote
0 answers

Runtime ~100X higer when return a graph with tf.function and serving

I have a simple tf.function to calculate sum of entries from a mask; noticed runtime is around .25s on my laptop, each time the function is called for serving (after warmup). when I return 0 instead of my_var the runtime is 3 orders lower, ~0.003.…
smm70
  • 11
  • 1
1
vote
1 answer

How do I invoke a data enrichment function before model.predict while serving the model in Databricks

In Databricks, I have used mlflow and got my model served through REST API. It works fine when all model features are provided. But my use case is that only a single feature (the primary key) will be provided by the consumer application, and my code…
1
vote
1 answer

Kubeflow missing .kube/config files on local setup (Laptop/Desktop)

I have installed Kubeflow via MiniKF on my laptop. I am trying to run a CNN on some MNIST data that uses TensorFlow 1.4.0. Currently, I am following this tutorial: https://codelabs.arrikto.com/codelabs/minikf-kale-katib-kfserving/index.html#0 The…
1
vote
2 answers

send post request using curl to mlflow api to multiple records

I have served an mlflow model and am sending POST requests in this format: curl -X POST -H "Content-Type:application/json; format=pandas-split" --data '{"columns":["alcohol", "chlorides", "citric acid", "density", "fixed acidity", "free sulfur…
1
vote
3 answers

Serving files with JSF 2 / CDI, using bookmarkable URLs

My main question is : Is there a "good practice" to serve binary files (PDF, docs, etc) using JSF 2 with CDI, and using bookmarkable URLs ? I've read the JSF 2 spec (JSR 314) and I see it exists a "Resource Handling" paragraph. But it seems to be…
Anthony O.
  • 22,041
  • 18
  • 107
  • 163
1
vote
1 answer

Tensorflow Serving using Docker

I have created a Neural Network Regression Model and I wish to deploy it using AWS. I am using tensorflow serving, and have gone so far as to save the model. Now I am trying to use Docker to deploy it in the container using Docker on Windows 10…
Prasinus Albus
  • 406
  • 1
  • 3
  • 21
1
vote
2 answers

How to serve protected images from static server (CDN)

I need to serve static content (mostly images) to logged users, but those images cannot be public. There is basic JWT authorization for clients. Those clients have images, but those images must be private (Only user who owns them can access…
Baterka
  • 3,075
  • 5
  • 31
  • 60
1
vote
0 answers

How to choose one appointed GPU when run tensorflow serving with docker

Like the title. I want to know how to choose one appointed GPU when run tensorflow serving with docker?
zheyuan xu
  • 11
  • 2
1
vote
1 answer

Testing TF serving model fails with bytes as strings and strings as bytes confusion

I'm having a problem serving my text classification model on Tensorflow 1.12. I'm using tf.estimator.inputs.pandas_input_fn to read in my data, and tf.estimator.DNNClassifier to train/evaluate. I'd then like to serve my model. (Apologies in advance,…
jwsmithers
  • 276
  • 2
  • 5
  • 15
1
vote
1 answer

Access locally served files within an R session

Context In order to test the web capabilities of an R package I am writing, I'm attempting to serve a file locally use the httpuv package so that I can run tests using an offline copy of the page. Issue However, curl doesn't seem to want to play…
owenjonesuob
  • 117
  • 8