Add more models

[xvjiarui]

This PR added ResNet18, ResNet18V1c, ResNet50 for FCN, DeeplabV3, DeeplabV3+, PSPNet.

[codecov]

Codecov Report

Merging #316 (0aa4cae) into master (feefc6a) will increase coverage by 0.78%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master     #316      +/-   ##
==========================================
+ Coverage   85.69%   86.47%   +0.78%     
==========================================
  Files          91       95       +4     
  Lines        4487     4761     +274     
  Branches      716      765      +49     
==========================================
+ Hits         3845     4117     +272     
- Misses        497      499       +2     
  Partials      145      145              

Flag	Coverage Δ
unittests	86.47% <ø> (+0.78%)	⬆️

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

Impacted Files	Coverage Δ
mmseg/models/backbones/__init__.py	100.00% <0.00%> (ø)
mmseg/models/decode_heads/__init__.py	100.00% <0.00%> (ø)
mmseg/models/decode_heads/dm_head.py	93.75% <0.00%> (ø)
mmseg/models/decode_heads/lraspp_head.py	100.00% <0.00%> (ø)
mmseg/models/backbones/mobilenet_v3.py	97.47% <0.00%> (ø)
mmseg/models/utils/se_layer.py	100.00% <0.00%> (ø)
mmseg/models/utils/inverted_residual.py	100.00% <0.00%> (+8.00%)	⬆️
mmseg/models/utils/make_divisible.py	100.00% <0.00%> (+42.85%)	⬆️

---

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 feefc6a...0aa4cae. Read the comment docs.

[hellock]

Task linked: CU-5qx2nb ResNet18, ResNet50, ResNet18V1c models