What is the difference of an executor and a predictor handle?

Open

#79 opened on Apr 20, 2017 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty: 3/5
Estimated time: 1-2 days
Newbie friendliness: 25/100

Issue type: Documentation
Clarity: Needs clarification
Activity status: Stale
Tech stack: cpp
Domain: api, machine-learning

Research direction

Start with the MXNet C++ API documentation for executor, predictor handles, MXPredSetInput, batch scoring, and loading a saved model. Done means clearly documenting which handle supports batched input and how a saved model is used, without relying on an unanswered issue thread.

Written by the indexing model from the issue text.

Description

If I want to score in batches using cpp api, should I use executor or predictor handle?
It seems MXPredSetInput can only accept single image instead of batch of images, correct?
If I need to use executor, how to create one from a saved model?

Dominant language: C++
Stars: 113
Forks: 78
PR merge metrics: No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

Read the whole issue, then the project's contributing guide.
Comment on the issue to say you are picking it up — it saves two people doing the same work.
Fork the repository and make your change on a branch.
Open a pull request that references the issue number.

Similar issues

rate_limit_sni_expiry AuTest is flaky: the holder races FIFO removal Open

AuTest Bug Tests

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

apache/trafficserver#13714 · Opened Sep 22, 2026
[CI] Nightly Clang build broken: ToJsonFunction no longer binds to registerFunction Open

bug build

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

facebookincubator/velox#19143 · Opened Sep 22, 2026
Misc. bug: Vulkan: ggml_backend_vk_get_device_memory reports free > total when the driver's heapBudget exceeds heap size (Intel iGPU, Windows); downstream consumers underflow Open

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

ggml-org/llama.cpp#29277 · Opened Sep 22, 2026
tt_metal/hw/inc/internal/tt-2xx/quasar/overlay/xcustom_test.hpp needs reimplementing Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

tenstorrent/tt-metal#57393 · 1 comment · Opened Sep 22, 2026
Ford-Fulkerson entry point sizes the graph by argument count, not by vertex id range, so it crashes on any vertex id >= args.length Open

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

objectionary/eo-graphs#74 · Opened Sep 22, 2026

More C++ issues