[Fix] Fix data collate and scatter in inference

[ly015]

Motivation

• Correct samples_per_gpu argument of collate() in inference
• Use scatter() instead of manually scatterring DataContainer
• Remove LoadImage and directly use test_pipeline of the model. Modify LoadImageFromFile to support manually set 'img' in results.

Modification

BC-breaking (Optional)

Use cases (Optional)

Checklist

Before PR:

• I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
• Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
• Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
• New functionalities are covered by complete unit tests. If not, please add more unit tests to ensure correctness.
• The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

• CLA has been signed and all committers have signed the CLA in this PR.

[CLAassistant]

All committers have signed the CLA.

[codecov]

Codecov Report

❗ No coverage uploaded for pull request base (dev-0.24@fd1e4fb). Click here to learn what that means.
The diff coverage is n/a.

@@             Coverage Diff             @@
##             dev-0.24    #1175   +/-   ##
===========================================
  Coverage            ?   82.72%           
===========================================
  Files               ?      204           
  Lines               ?    16349           
  Branches            ?     2942           
===========================================
  Hits                ?    13525           
  Misses              ?     2079           
  Partials            ?      745           

Flag	Coverage Δ
unittests	82.66% <0.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update fd1e4fb...a911775. Read the comment docs.