Skip to main content

TF Served Model Over Docker Missing Model Information, Returns 404 If Requested

I have a trained model I am trying to deploy an image classifier through tensorflow serving in a Docker container. When I run my python code to request over REST I get a 404 response. The request looks as so:

json_response = requests.post('http://localhost:8501/models/model_name:predict', data=data)
json_response.raise_for_status()

prediction = json_response.json()['predictions'][0]
print(prediction)

Upon inspection of the model information using curl, I get this in response:

<HTML><HEAD>
<TITLE>404 Not Found</TITLE>
</HEAD><BODY>
<H1>Not Found</H1>
</BODY></HTML>

I followed the instructions from the tensorflow website on serving with docker and had no errors during the setup.

I believe it may have something to do with the way that I saved my model, since examples in the tf_serving guide worked, but I had used the SavedModel format as outlined on tensorflow the code for which is here:

tmpdir = tempfile.mkdtemp()
save_path = os.path.join(tmpdir, "model_name/1/")

print(list(model.signatures.keys()))  # ["serving_default"]

infer = model.signatures["serving_default"] # 5 classes
print(infer.structured_outputs)

tf.saved_model.save(model, save_path)

The print statements for the prior code:

['serving_default']
{'dense_2': TensorSpec(shape=(None, 5), dtype=tf.float32, name='dense_2')}

In the tensorflow SavedModel guide it shows the structured output having the name "predictions", which may be part of the issue.

For reference, I am using transfer learning from a frozen MobileNetV2, with a few added layers.

I am fairly new to both Tensorflow and Tensorflow Serving, so please forgive me if this is a simple issue i may have missed.



source https://stackoverflow.com/questions/76030045/tf-served-model-over-docker-missing-model-information-returns-404-if-requested
Labels:

Comments

Post a Comment

Popular posts from this blog

Why is my reports service not connecting?

I am trying to pull some data from a Postgres database using Node.js and node-postures but I can't figure out why my service isn't connecting. my routes/index.js file: const express = require('express'); const router = express.Router(); const ordersCountController = require('../controllers/ordersCountController'); const ordersController = require('../controllers/ordersController'); const weeklyReportsController = require('../controllers/weeklyReportsController'); router.get('/orders_count', ordersCountController); router.get('/orders', ordersController); router.get('/weekly_reports', weeklyReportsController); module.exports = router; My controllers/weeklyReportsController.js file: const weeklyReportsService = require('../services/weeklyReportsService'); const weeklyReportsController = async (req, res) => { try { const data = await weeklyReportsService; res.json({data}) console...
Post a Comment
Read more

How to show number of registered users in Laravel based on usertype?

i'm trying to display data from the database in the admin dashboard i used this: <?php use Illuminate\Support\Facades\DB; $users = DB::table('users')->count(); echo $users; ?> and i have successfully get the correct data from the database but what if i want to display a specific data for example in this user table there is "usertype" that specify if the user is normal user or admin i want to user the same code above but to display a specific usertype i tried this: <?php use Illuminate\Support\Facades\DB; $users = DB::table('users')->count()->WHERE usertype =admin; echo $users; ?> but it didn't work, what am i doing wrong? source https://stackoverflow.com/questions/68199726/how-to-show-number-of-registered-users-in-laravel-based-on-usertype
Post a Comment
Read more

The number of nodes and edges I calculated manually and by a method provided by networkx library dont match

I am trying to analyse a graph using networkx library in Python. I have implemented a function that returns the nodes and edges of that graph. After that I counted the number of nodes and edges by implementing the len() function for nodes and edges, which gave me 17 for both nodes and edges. However, when I used the method graph.number_of_nodes() of networkx library it gave me 53. My code: import pandas as pd import networkx as nx import matplotlib.pyplot as plt header_list = ["a","b","w"] E =pd.read_csv("aves-barn-swallow-contact-network.edges",sep=" ",header= None,names=header_list) # print(E.head()) # prints first few rows of the csv file G = nx.from_pandas_edgelist(E,"a","b",["w"]) nx.draw(G) plt.show() class GraphAnalyse: #finding nodes and edges def nodeEdge(self,Graph): nodes = Graph.nodes() edges = Graph.edges() ...
Post a Comment
Read more