[Application] Transfer learning example on Resnet-18

[Application] Transfer learning example on Resnet-18

I added transfer learning option to resnet-18 example.

If this option is enabled, then load pre-trained weights
and freeze the weights of backbone(feature extractor).
(It just a simple transfer learning).

You can make pre-trained weights using save_bin function
from our pytorch resnet-18 example.

**Self evaluation:**
1. Build test:	 [X]Passed [ ]Failed [ ]Skipped
2. Run test:	 [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: Seungbaek Hong <sb92.hong@samsung.com>