[PyTorch] add cuDNN acceleration

[lanking520]

Description

Inspired from PyTorch performance tuning thread: https://pytorch.org/tutorials/recipes/recipes/tuning_guide.html#enable-cudnn-auto-tuner

Adding for Resnet and YOLO V5 related model speed up with this flag

[codecov-commenter]

Codecov Report

Merging #1592 (c667f67) into master (bb5073f) will decrease coverage by 1.23%.
The diff coverage is 60.41%.

@@             Coverage Diff              @@
##             master    #1592      +/-   ##
============================================
- Coverage     72.08%   70.85%   -1.24%     
- Complexity     5126     5400     +274     
============================================
  Files           473      504      +31     
  Lines         21970    23612    +1642     
  Branches       2351     2567     +216     
============================================
+ Hits          15838    16731     +893     
- Misses         4925     5602     +677     
- Partials       1207     1279      +72     

Impacted Files	Coverage Δ
api/src/main/java/ai/djl/modality/cv/Image.java	69.23% <ø> (-4.11%)	⬇️
...i/djl/modality/cv/translator/BigGANTranslator.java	21.42% <ø> (-5.24%)	⬇️
...odality/cv/translator/BigGANTranslatorFactory.java	33.33% <0.00%> (+8.33%)	⬆️
...nslator/InstanceSegmentationTranslatorFactory.java	14.28% <0.00%> (-3.90%)	⬇️
.../modality/cv/translator/YoloTranslatorFactory.java	8.33% <0.00%> (-1.67%)	⬇️
...i/djl/modality/cv/translator/YoloV5Translator.java	5.69% <0.00%> (ø)
...odality/cv/translator/YoloV5TranslatorFactory.java	8.33% <0.00%> (-1.67%)	⬇️
...pi/src/main/java/ai/djl/ndarray/BytesSupplier.java	54.54% <0.00%> (-12.13%)	⬇️
...ain/java/ai/djl/ndarray/index/dim/NDIndexPick.java	100.00% <ø> (ø)
api/src/main/java/ai/djl/nn/Blocks.java	75.00% <0.00%> (-25.00%)	⬇️
... and 235 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 bbdcbf7...c667f67. Read the comment docs.