We have tried deploying our own model as a pipeline with Clara Deploy SDK, but runs into an error.
- Using our own trained model from CLARA Train SDK
- We changed model.trt.pb to model.graphdef by renaming file
- Write config.pbtxt for the model
- labels.txt contains 1 line (our demo model is binary classification)
- Runs into an error in the next page when infer images
We follow the procedure from the URL below.
my config_inference.json in the URL below