keras-team/autokeras

Specify hyperparameter ranges for blocks

Open

#1,420 opened on Nov 5, 2020

View on GitHub
 (19 comments) (0 reactions) (0 assignees)Python (9,025 stars) (1,420 forks)batch import
contribution welcomefeature requestgood first issuepinned

Description

Feature Description

We want to enable the users to specify the value ranges for any argument in the blocks. The following code example shows a typical use case. The users can specify the number of units in a DenseBlock to be either 10 or 20.

Code Example

import autokeras as ak
from kerastuner.engine.hyperparameters import Choice

input_node = ak.ImageInput()
output_node = ak.DenseBlock(num_units=Choice("num_units", [10, 20]))(input_node)
output_node = ak.ClassificationHead()(output_node)
model = ak.AutoModel(input_node, output_node)

Note

Each pull request should only change one hyperparameter in one of the blocks.

Solution

Example pull requests are #1419 #1425 . Here are the steps to follow:

  1. You can just change any other argument in any other block supported by AutoKeras, as shown here.
  2. Change the docstring. example
  3. Make sure you imported the module. from kerastuner.engine import hyperparameters.
  4. Change the typing of the argument. example
  5. Change the saving mechanism to serialized objects. example
  6. Change the loading mechanism to deserialized objects. example
  7. Change how we initialize the hyperparameter to self. example Copy from where it is originally defined. example
  8. Change how we use it. example

Contributor guide

Tech stack
python
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Python programmingBasic understanding of AutoKerasFamiliarity with kerastuner hyperparameters
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80
Research direction
The issue provides a detailed step by step guide for implementing the feature. The contributor should pick a hyperparameter in one of the blocks (see autokeras/ init .py lines 16-38 for list of blocks). Follow the pattern from PRs #1419 and #1425: modify the argument to accept a Choice object, update docstring, change typing, adjust save/load mechanisms, and update usage. The work is localized to a single block per PR.
Specify hyperparameter ranges for blocks · keras-team/autokeras#1420 | Good First Issue