You can deploy this model and start earning money today!

tqphu12421/
tf-ddp

Name: tf-ddp
Availability: InStock

Views

No views yet

Quickstart

Build and start Machine Learning backend on http://localhost:9090

docker-compose up

Check if it works:

bash

$ curl http://localhost:9090/health
{"status":"UP"}

Then connect running backend to AIxBlockusing Machine Learning settings.

Writing your own model

Place your scripts for model training & inference inside root directory. Follow the API guidelines described bellow. You can put everything in a single file, or create 2 separate one say my_training_module.py and my_inference_module.py
Write down your python dependencies in requirements.txt
Open wsgi.py and make your configurations under init_model_server arguments:

python
1from my_training_module import training_script 2from my_inference_module import InferenceModel 3 4init_model_server( 5 create_model_func=InferenceModel, 6 train_script=training_script, 7 ...
Make sure you have docker & docker-compose installed on your system, then run

docker-compose up --build

API guidelines

Inference module

In order to create module for inference, you have to declare the following class:

python

from htx.base_model import BaseModel

# use BaseModel inheritance provided by pyheartex SDK 
class MyModel(BaseModel):
    
    # Describe input types (AIxBlockobject tags names)
    INPUT_TYPES = ('Image',)

    # Describe output types (AIxBlockcontrol tags names)
    INPUT_TYPES = ('Choices',)

    def load(self, resources, **kwargs):
        """Here you load the model into the memory. resources is a dict returned by training script"""
        self.model_path = resources["model_path"]
        self.labels = resources["labels"]

    def predict(self, tasks, **kwargs):
        """Here you create list of model results with Label Studio's prediction format, task by task"""
        predictions = []
        for task in tasks:
            # do inference...
            predictions.append(task_prediction)
        return predictions

Training module

Training could be made in a separate environment. The only one convention is that data iterator and working directory are specified as input arguments for training function which outputs JSON-serializable resources consumed later by load() function in inference module.