CODEWITHSUNDEEP
tensorflowtensorflow-servingstackdrivergoogle-cloud-stackdriver
Giri Bhushan Ch
Giri Bhushan Ch

Reputation: 21

How to setup logging for cloud ml-engine during serving/inference

After loading a checkpoint; I have exported the model and then copied the saved_model.pb file and all the variables to GCS bucket.

During inference/serving, I get this error:

{
  "error": "Prediction failed: Error during model execution: AbortionError(code=StatusCode.FAILED_PRECONDITION, details=\"Attempting to use uninitialized value shadow/LSTMLayers/stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/bias\n\t [[Node: shadow/LSTMLayers/stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/bias/read = Identity[T=DT_FLOAT, _output_shapes=[[2048]], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"](shadow/LSTMLayers/stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/basic_lstm_cell/bias)]]\")"
}

Please suggest me how to setup the logging at test/inference time in cloud ml-engine.

Upvotes: 1

Views: 248

Answers (1)

MatthewScarpino
MatthewScarpino

Reputation: 5926

If you've set up a GCP project, you can write messages to the log using the StackDriver Logging API. Then you can access log messages from the command line (gcloud logging) or from the developer console.

Upvotes: 1

Related Questions