feat(pix2pix): add inference batching

[AmitMY]

Fixes

Relates to #58

Description

Since GPUs are highly parallelizable, could we perform inference on multiple frames at once instead of one-by-one?

Yes, we can! However, it does not improve performance much if the GPU is weak.

Benchmark on Macbook Pro with M1 Max, shows no substantial improvement from batching. We observe a linear scale by batch size.

Batch Size	Fastest (ms)	Slowest (ms)
1	52.4	91.2
2	104.2	120.5
3	157.1	165.0
5	262.5	267.3
6	310.5	318.0

[coveralls]

Pull Request Test Coverage Report for Build 4641016751

• 0 of 8 (0.0%) changed or added relevant lines in 1 file are covered.
• 2 unchanged lines in 2 files lost coverage.
• Overall coverage increased (+0.6%) to 53.211%

---

Changes Missing Coverage	Covered Lines	Changed/Added Lines	%
src/app/pages/translate/pose-viewers/human-pose-viewer/human-pose-viewer.component.ts	0	8	0.0%

Files with Coverage Reduction	New Missed Lines	%
src/app/core/services/assets/assets.service.ts	1	39.66%
src/app/pages/translate/pose-viewers/human-pose-viewer/human-pose-viewer.component.ts	1	16.67%

Totals
Change from base Build 4618504967:	0.6%
Covered Lines:	1115
Relevant Lines:	2003

---

💛 - Coveralls

[github-actions]

Visit the preview URL for this PR (updated for commit 5d9fe2e):

https://translate-sign-mt--pr83-pix2pix-batching-q8o1qeuz.web.app

_{(expires Fri, 14 Apr 2023 20:17:00 GMT)}

_{🔥 via Firebase Hosting GitHub Action 🌎}

_{Sign: 739446cfe7a349700ebd347d2a39e3b90ba24425}