Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Has Anyone Used

Has anyone used clearml-serving and successfully sent an inference request via curl? I'm having trouble trying to send an inference request to the keras mnist model example in the github page

  
  
Posted 2 years ago
Votes Newest

Answers 14


platform: "tensorflow_savedmodel" input [ { name: "dense_input" data_type: TYPE_FP32 dims: [-1, 784] } ] output [ { name: "activation_2" data_type: TYPE_FP32 dims: [-1, 10] } ]

  
  
Posted 2 years ago

i don't know ahahaha

  
  
Posted 2 years ago

it's from the github issue you sent me but i don't know what the "application" part is or the "NV-InferRequest:...."

  
  
Posted 2 years ago

i'm just interested in actually running a prediction with the serving engine and all

  
  
Posted 2 years ago

i'm also not sure what this is
-H "Content-Type: application/octet-stream" -H' NV-InferRequest:batch_size: 1 input { name: "dense_input" dims: [-1, 784] } output { name: "activation_2" cls { count: 1 } }'

  
  
Posted 2 years ago

img.tofile('7.binaryimage',format='binary') can this be the issue?

  
  
Posted 2 years ago

well, i have run the keras mnist example that is in the clearml-serving READme. Now I'm just trying to send a request to make a prediction via curl

  
  
Posted 2 years ago

Hmm I seems to fit the code 1x784 with float32, no?

  
  
Posted 2 years ago

So far I have taken one mnist image, and done the following:

` from PIL import Image
import numpy as np

def preprocess(img, format, dtype, h, w, scaling):

sample_img = img.convert('L')


resized_img = sample_img.resize((1, w*h), Image.BILINEAR)
resized = np.array(resized_img)
resized = resized.astype(dtype)

return resized

png img file

img = Image.open('./7.png')

preprocessed img, FP32 formated numpy array

img = preprocess(img, format, "float32", 28, 28, None)

to bytes

img = img.tofile('7.binaryimage',format='binary') curl -X POST 192.168.34.174:8000/v2/models/keras_mnist/versions/1 -H "Content-Type: application/octet-stream" -H' NV-InferRequest:batch_size: 1 input { name: "dense_input" dims: [-1, 784] } output { name: "activation_2" cls { count: 1 } }' --data-binary "@7.binaryimage" `

  
  
Posted 2 years ago

fp32 seems to be floating point 32 so my preprocessing seems wrong

  
  
Posted 2 years ago

i can't get some sort of response from curl

  
  
Posted 2 years ago

ElegantCoyote26 what is the model input layer definition? This implies the data format to pass to the serve endpoint

  
  
Posted 2 years ago

ElegantCoyote26 , Hi 🙂

Can you provide an example of what you're trying to do?

  
  
Posted 2 years ago

i'm probably sending the request all wrong + i'm not sure how the model expects the input

  
  
Posted 2 years ago
910 Views
14 Answers
2 years ago
one year ago
Tags