[v1.x] Update unittests for object detection models

[waytrue17]

Description

To address the prediction mismatching due to different implementations of nms operator between mxnet and onnx.

Checklist

Essentials

• PR's title starts with a category (e.g. [BUGFIX], [MODEL], [TUTORIAL], [FEATURE], [DOC], etc)
• Changes are complete (i.e. I finished coding on this PR)
• All changes have test coverage
• Code is well-documented

Changes

• Feature1, tests, (and when applicable, API doc)
• Feature2, tests, (and when applicable, API doc)

Comments

• If this change is a backward incompatible change, why must this change be made.
• Interesting edge cases to note here

[mxnet-bot]

Hey @waytrue17 , Thanks for submitting the PR
All tests are already queued to run once. If tests fail, you can trigger one or more tests again with the following commands:

• To trigger all jobs: @mxnet-bot run ci [all]
• To trigger specific jobs: @mxnet-bot run ci [job1, job2]

---

CI supported jobs: [windows-gpu, centos-cpu, miscellaneous, edge, website, clang, centos-gpu, sanity, unix-cpu, unix-gpu, windows-cpu]

---

Note:
Only following 3 categories can trigger CI :PR Author, MXNet Committer, Jenkins Admin.
All CI tests must pass before the PR can be merged.

[waytrue17]

@mxnet-bot run ci [sanity]

[mxnet-bot]

Jenkins CI successfully triggered : [sanity]

[waytrue17]

@mxnet-bot run ci [centos-gpu, edge]

[mxnet-bot]

Jenkins CI successfully triggered : [edge, centos-gpu]

[josephevans]

LGTM, thanks!

[waytrue17]

@mxnet-bot run ci [edge]

[mxnet-bot]

Jenkins CI successfully triggered : [edge]