Migrate examples to use depthai 2.0.0.1 and follow a common blob naming format

[VanDavv]

While migrating examples to the latest PyPi release, and making sure the blobs are using the latest OpenVINO and have correct blob names, I found two examples that stopped working as they used to:

• Pedestrian Reidentification network (person-reidentification-retail-0031) is no longer available in 2021.2, was removed in 2020.4. The new network that I tried to use - person_reidentification_retail_0288 and person_reidentification_retail_0277 - accept an input image in higher resolution (now 128x256, previously 48x96), which may be a cause of a significant inference speed drop when these networks start to process the frames.

  Code for this example is here as was not included in this PR due to the performance issues

• Tensorflow Image Classification example has accuracy issues when model is changed to the one compiled for 6 or 8 shaves. Where previously is recognized a dandelion (like on a demo image) it does no more. That's why this example is also not included in this PR, and its source code is here

Other than these two, the rest of the examples work fine.

[SzabolcsGergely]

You can use openvino IR model compiled for 2020.1/3/4 for person-reidentification-retail-0031 and use myriad compiler from 2021.2, it will likely work. That's how I compiled deeplabv3 for openvino 2021.2 since I had only 2020.1 IR model from gen1. @VanDavv

[VanDavv]

That's very clever, will do. Thanks @szabi-luxonis !

[SzabolcsGergely]

LGTM