pytorch/serve

Built-in handler for regression

Open

#987 opened on Mar 2, 2021

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Java (790 forks)batch import
enhancementgood first issue

Repository metrics

Stars
 (3,844 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Is your feature request related to a problem? Please describe.

Every model ultimately transforms an input tensor (array of numbers) to an output tensor (another array of numbers). This is the general case, yet there is no handler that could handle such a model.

Describe the solution

The base handler or a some new regression_handler should handle the case of predicting from a JSON list of numbers to a JSON list of numbers.

Contributor guide

Research direction
Study the existing base handler in torchserve and implement a new regression handler that accepts a JSON array of numbers as input and returns a JSON array of numbers as output. Refer to the handler development guide.
Tech stack
pythonjava
Domain
backendapimachine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchtorchserve
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70