pytorch_igniter.inference package

Submodules

pytorch_igniter.inference.audio_input_fn module

pytorch_igniter.inference.greyscale_image_input_fn module

pytorch_igniter.inference.greyscale_image_input_fn.input_fn(request_body, request_content_type)

Convert input for your model

pytorch_igniter.inference.image_input_fn module

pytorch_igniter.inference.image_input_fn.input_fn(request_body, request_content_type)

Convert input for your model

pytorch_igniter.inference.inference module

pytorch_igniter.inference.inference.model_fn(model_dir)

Load your model from model_dir

pytorch_igniter.inference.inference.predict_fn(input_data, model)

Run your model

pytorch_igniter.inference.json_output_fn module

class pytorch_igniter.inference.json_output_fn.TensorEncoder(*, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, sort_keys=False, indent=None, separators=None, default=None)

Bases: json.encoder.JSONEncoder

default(obj)

Implement this method in a subclass such that it returns a serializable object for o, or calls the base implementation (to raise a TypeError).

For example, to support arbitrary iterators, you could implement default like this:

def default(self, o):
    try:
        iterable = iter(o)
    except TypeError:
        pass
    else:
        return list(iterable)
    # Let the base class default method raise the TypeError
    return JSONEncoder.default(self, o)

pytorch_igniter.inference.json_output_fn.output_fn(prediction, content_type)

Convert model output

Module contents