Skip to main content

Python package for querying ModelZoo.Live

Project description

ModelZoo

Python package to query ModelZoo.Live

API

For more specific API details, please check out the docs within the files.

Examples

Initialization

# Connects to a ModelZoo instance running at http://modelzoo.url/
conn = ModelZooConnection(address="http://modelzoo.url/")
# Authenticate to service. Neccessary to see your token.
conn.authenticate("myemail@me.com", "mypassword")

Get Models

# Assuming conn initialized previously
conn.list_all_models()

Get Token

# Assuming conn initialized previously, and authenticated to server
conn.get_token()

Create User

# Assuming conn initialized previously
conn.create_user("mynewemail@me.com", "mynewpassword")

Text Inference

# Assuming conn initialized previously
model_name = "MyModelName"
input = ["Input1", "Input2"]

p = conn.text_inference(model_name, input)
# type(p) = modelzoo.protos.Payload

If your model's output is text, you could expect an output formatted like so:

p = Payload({type: PayloadType.TEXT, text = t})
t = Text({metadata: {...}, texts: ["output1", ...], model_name: "name", access_token: "token"})

Image Inference

# Assuming img is your image input.
# img can be oneof(filename, PIL.Image, image data uri)
model_name = "MyModelName"

p = conn.image_inference(model_name, img)
# type(p) = modelzoo.protos.Payload

If your model's output is an image, you could expect an output formatted like so:

p = Payload({type: PayloadType.IMAGE, image = t})
t = Image({metadata: {...}, image_data_url: "img_output_uri", model_name: "name", 
           access_token: "token"})

It is important to note that your model is not constrained to return an output of the same type as its input.

It is perfectly valid, for example, for a model to take a text input, and return an image output, or vice versa.

Extracting Output for Inference

...
# p is the Payload object returned by
# oneof(text_inference, image_inference)
if p.type == PayloadType.TEXT:
    out = sugar.text_input(p.text)
elif p.type == PayloadType.IMAGE:
    out = sugar.image_input(p.image)
# out = oneof(List[string], PIL.Image)

Post Processing for Inference

...
# p is the Payload object returned by
# oneof(text_inference, image_inference)
def callback(input):
    # Input is oneof(pd.DataFrame, List[string], PIL.Image)
    return output

o = conn.process_inference_response(p, callback)

# o == callback(extract(payload))

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for modelzoo, version 0.3.2
Filename, size File type Python version Upload date Hashes
Filename, size modelzoo-0.3.2-py3-none-any.whl (18.5 kB) File type Wheel Python version py3 Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page