DensePose fine person segmentation

## ❓ How can we use densepose/detectron2 in order to get only fine person segmentation (faster than just using the apply_net.py provided as example)

We are using an already trained model (densepose_rcnn_R_50_FPN_s1x.yaml). We would like to built on top of densepose but we require 5-6 FPS and we are only interested on the fine person segmentation.
We are executing the apply_net.py with CUDA 10.2 in a GTX1080 Ti and the model execution takes ~2.2 seconds (the snipped code prints Time required: 2.2)
```
with torch.no_grad():
a=time.time()
outputs = predictor(img)["instances"]
print("Time required: ",time.time()-a)
cls.execute_on_outputs(context, {"file_name": file_name, "image": img}, outputs) #This does not really matter for us now
```
We would like to know if there is a possible way to speed up the "predictor(img)" by changing the configuration files (we use the default provided by the getting started guide [configs/densepose_rcnn_R_50_FPN_s1x.yaml]).

Thanks in advanced,

Start with apply_net.py and the predictor(img) call, then inspect configs/densepose_rcnn_R_50_FPN_s1x.yaml to understand which parts of the model are executed. Reproduce the reported ~2.2-second timing on the stated CUDA 10.2 and GTX1080 Ti setup; done would mean identifying a supported configuration or execution path that reaches the requested 5–6 FPS while retaining fine person segmentation.

Written by the indexing model from the issue text.