Deep Person Reid Versions Save

• Removed unused imports/variables.
• Fixed minor bugs.

Basically a more stable version.

Added new dataset, models and tools.

Major updates:

• Significant changes to "scripts/main.py", where most arguments in argparse are replaced with config.
• Add config files which contain predefined training params to configs/.
• In data manager and engine, use_cpu is changed to use_gpu.
• In data manager, batch_size is changed to batch_size_train and batch_size_test.
• Tensorboard is available.

Main update:

• Plot ranks in a single figure (currently support image-reid)
• Visualize activation maps to understand where CNNs focus on to extract features for reid.

Bug fix: resize image to the target size in the training transformation function

• Add OSNet code and models

• Model zoo is back.
• Some minor updates.

Major updates:

• Added compute_model_complexity().
• Added shufflenetv2.

Major updates:

• Added person reranking, which can be activated with rerank=True in engine.run(). It only works in the evaluation mode, i.e. test_only=True.
• Added normalize_feature to engine.run() to allow the feature vectors to be normalized with L2 norm before calculating feature distance.

Major changes:

• Added conda install instructions.
• Fixed a bug in learning rate scheduler https://github.com/KaiyangZhou/deep-person-reid/commit/dcd8da565a9802bf48e8694e616e633a51b413a3
• Fixed a bug in combineall https://github.com/KaiyangZhou/deep-person-reid/commit/bb6dc46e21e335789b9d891f7191c1da3a5d2e01