Google explainable ai 429 error Rate of traffic exceeds serving capacity. Decrease your traffic or reduce the size of your model

Question

I'm trying to interpret an image prediction model using Google's explainable ai, but I get a 429 error. The model I want to interpret is a model that uses the mobilenet v3 large model and applies transfer learning.

python code :

ig_response = remote_ig_model.explain(instances)

results :

ValueError: Target URI https://asia-northeast1-        ml.googleapis.com/v1/projects/cellimaging/models/A549_4/versions/v_ig_4:explain returns     HTTP 429 error.
Please check the raw error message: 
{
  "error": {
    "code": 429,
    "message": "Rate of traffic exceeds serving capacity. Decrease your traffic or reduce the size of your model: projects/842842301933/models/A549_4/versions/v_ig_4.",
    "status": "RESOURCE_EXHAUSTED"
  }
}

When creating a serving model using ai-platform, the command is as follows.

code :

! gcloud beta ai-platform versions create $IG_VERSION --region='asia-northeast1' \
--model $MODEL \
--origin $export_path \
--runtime-version 2.2 \
--framework TENSORFLOW \
--python-version 3.7 \
--machine-type n1-highcpu-32 \
--explanation-method integrated-gradients \
--num-integral-steps 25

I got a 429 error and tried changing the machine-type (n1-standard-4 -> n1-highcpu-32), but the error is not resolved.

Answer 1

You can have a look on this troubleshoot section, your request can't be larger than 1.5Mb

A single online prediction request must contain no more than 1.5 MB of data.

If you have an input of 1024,1024,3, your image size should be 3Mb (1024 x 1024 x 3 bytes) and therefore too big for the API.