Upload video models

[fmassa]

They give the follow accuracies

Network	Clip acc@1	Clip acc@5
ResNet 3D 18	52.75	75.45
ResNet MC 18	53.90	76.29
ResNet (2+1)D	57.50	78.81

Entries in the documentation with those values are added in #1207

[codecov-io]

Codecov Report

Merging #1208 into master will increase coverage by 0.32%.
The diff coverage is n/a.

@@            Coverage Diff            @@
##           master   #1208      +/-   ##
=========================================
+ Coverage   65.27%   65.6%   +0.32%     
=========================================
  Files          74      74              
  Lines        5780    5780              
  Branches      883     883              
=========================================
+ Hits         3773    3792      +19     
+ Misses       1736    1724      -12     
+ Partials      271     264       -7

Impacted Files	Coverage Δ
torchvision/models/video/resnet.py	79.52% <ø> (ø)	⬆️
torchvision/transforms/transforms.py	80.94% <0%> (+0.78%)	⬆️
torchvision/transforms/functional.py	71.38% <0%> (+0.86%)	⬆️
torchvision/datasets/lsun.py	22.91% <0%> (+2.08%)	⬆️
torchvision/datasets/voc.py	23.07% <0%> (+2.19%)	⬆️
torchvision/datasets/folder.py	82.05% <0%> (+2.56%)	⬆️
torchvision/datasets/cifar.py	78.16% <0%> (+6.89%)	⬆️

---

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 1afef1d...d075d13. Read the comment docs.