DensePose fails on certain images

## Instructions To Reproduce the 🐛 Bug:
1. Full runnable code or full changes you made:
```
no changes
```
2. What exact command you run: python apply_net.py dump configs/densepose_rcnn_R_101_FPN_DL_s1x.yaml densepose_rcnn_R_101_FPN_DL_s1x.pkl "image_fail*.jpg" --output results.pkl -v
3. __Full logs__ or other relevant observations:
```
data: [{'file_name': 'image_fail.jpg', 'scores': tensor([]), 'pred_boxes_XYXY': tensor([], size=(0, 4))}]

Also attaching image which causes densepose to fail.

```

4. please simplify the steps as much as possible so they do not require additional resources to
run, such as a private dataset.

## Expected behavior:

To get values corresponding to all fields listed in 3. above.

## Environment:

Provide your environment information using the following command:
```
---------------------- -------------------------------------------------------------------------------------------
sys.platform linux
Python 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0]
numpy 1.19.2
detectron2 0.3 @/media/shubhendujena/DATA/Subset_experiments/detectron2/detectron2
Compiler GCC 9.3
CUDA compiler CUDA 10.1
detectron2 arch flags 7.5
DETECTRON2_ENV_MODULE
PyTorch 1.7.1 @/home/shubhendujena/anaconda3/envs/Shubhendu/lib/python3.7/site-packages/torch
PyTorch debug build False
GPU available True
GPU 0 Quadro RTX 5000 (arch=7.5)
CUDA_HOME /usr
Pillow 8.1.0
torchvision 0.8.2 @/home/shubhendujena/anaconda3/envs/Shubhendu/lib/python3.7/site-packages/torchvision
torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5, 8.0
fvcore 0.1.2.post20210115
cv2 4.1.1
---------------------- -------------------------------------------------------------------------------------------
PyTorch built with:
- GCC 7.3
- C++ Version: 201402
- Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 11.0
- NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_37,code=compute_37
- CuDNN 8.0.5
- Magma 2.5.2
- Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON,

Start by running the supplied Python command with image_fail.jpg, then inspect apply_net.py, the DensePose configuration, and the checkpoint named in the command. Compare the empty scores and bounding-box outputs with the expected fields in the report; done means the image produces values for all those fields.

Written by the indexing model from the issue text.