Skip to main content

Network builder for bigml deepnet topologies

Project description

BigML Sense/Net

Sense/Net is a BigML interface to Tensorflow, which takes a network specification as a dictionary (read from BigML's JSON model format) and instantiates a tensorflow compute graph based on that specification.

Entry Points

The library is meant, in general, to take a BigML model specification and an optional map of settings and return a tf.keras.Model based on these arguments.

Deepnets

The class sensenet.models.deepnet.DeepnetWrapper exposes this functionality for BigML deepnet models. To instantiate one of these, pass the model specification and the map of additional settings:

model = sensenet.models.deepnet.DeepnetWrapper(model_dict, settings)

Again, model_dict is typically the relevant section from the downloaded BigML model, and settings is a map of optional settings which may contain:

  • image_path_prefix: A string directory indicating the path where images are to be found for image predictions. When an image path is passed at prediction time, this string is prepended to the given path.

  • input_image_format: The format of input images for the network. This can be either an image file on disk (file) or a string containing the raw image bytes (bytes)

Once instantiated, you can use the model to make predictions:

model.predict([1.0, 2.0, 3.0])

The input point or points must be a list (or nested list) containing the input data for each point, in the order implied by model._preprocessors. Categorical and image variables should be passed as strings, where the image is either a path to the image on disk, or the raw compressed image bytes.

The function returns a numpy array where each row is the model's prediction for each input point. For classification models, there will be a probability for each class in each row. For regression models, each row will contain only a single entry.

Project details


Download files

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

Source Distribution

bigml-sensenet-0.2.3.tar.gz (25.0 kB view details)

Uploaded Source

File details

Details for the file bigml-sensenet-0.2.3.tar.gz.

File metadata

  • Download URL: bigml-sensenet-0.2.3.tar.gz
  • Upload date:
  • Size: 25.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.6.0 requests-toolbelt/0.9.1 tqdm/4.45.0 CPython/3.7.7

File hashes

Hashes for bigml-sensenet-0.2.3.tar.gz
Algorithm Hash digest
SHA256 662d1509997af7286193003fc68ddf500c7c1847a2d70bf5f3fbe78d3372ca87
MD5 46c345e45b523656ccffb390928f074e
BLAKE2b-256 0e3e08916a98b61209d08eb3e18c5a21d79a088437dd681098eacddd667f86c3

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page