How can I use it on COCO-DataSet？

[qinziqiao]

How to do if I want to do argument on COCO ，though I have known the project developed on VOC-Dataset.

[dvornikita]

Hi, The guidelines for adapting the pipeline for the COCO dataset are the following:

1. Build the COCO loader that has the same methods and attributes as the VOC PASCAL one (dataset/voc_loader.py). It's best to build on top of pycocotools.
2. Extract COCO instances into dedicated folders (analogous to the pascal)
3. Train the context model on the coco dataset, perform inference to score the locations and perform location-instance matching (analogous to the pascal, described in the readme)
4. Adapt context_aug/instance_manipulators.py to support COCO loader and to load instances from the dedicated folder. You will probably have to read instances from the disc each time you want to use one since all the coco instances won't fit into memory as opposed to PASCAL. For that, you will need to modify the init of the DynamicInstanceManipulator class.

This should be enough from what I recall. Best

[qinziqiao]

Thank you very much. I'll try it .