Allow more than one image per GPU during evaluation

[maktu6]

• It allows muti-images for one GPU during the testing time, which was metioned in is it something wrong that the code returns only one image' label and mask in mask_head? #7.
  I have only checked ResNet-50-FPN-MS-RCNN on coco_2017_val via single GPU. Note that MODEL.RPN.FPN_POST_NMS_TOP_N_TEST also needs to be changed, see here for more details.
• I also modify model_zoo.py which would raise an ImportError in PyTorch 1.1 and update paths_catalog.py to support coco 2017.

python tools/test_net.py --config-file "configs/e2e_ms_rcnn_R_50_FPN_1x.yaml" \
                                       TEST.IMS_PER_BATCH 5 \
                                       MODEL.RPN.FPN_POST_NMS_TOP_N_TEST 5000 \
                                       MODEL.WEIGHT pretrained_models/res50-model_0090000.pth \
                                       DATASETS.TEST "('coco_2017_val',)" 

The following are the evaluation results which are the same as yours:

Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=45.91s).
Accumulating evaluation results...
DONE (t=5.32s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.379
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.593
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.411
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.222
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.408
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.497
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.312
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.491
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.516
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.329
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.549
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644

Running per image evaluation...
Evaluate annotation type *segm*
DONE (t=51.75s).
Accumulating evaluation results...
DONE (t=5.53s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.356
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.561
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.382
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.166
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.378
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.519
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.297
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.453
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.471
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.275
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.505
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.617