Add dim check while calculating mIoU&pixAcc for segmentation test

[chunhanl]

1. The test.py example mentioned at
   segmentation.rst
   does not match the arguments mentioned in test.py
   should probably be change to
   python test.py --dataset ade20k --pretrained --model fcn --backbone resnet50 --eval

2. The dimension doesn't seem right when calculating the pixACC and mIoU
   The output is 3D and the target is 2D
   The safest way I could think of is to add a new axis if batch dim is missing.
   Might have a better way to deal with.

Result after modification (without training)

[chunhanl]

Apologies for the new spaces, it was automatically modified by Pycharm IDE

[mli]

Job PR-991-1 is done.
Docs are uploaded to http://gluon-vision-staging.s3-website-us-west-2.amazonaws.com/PR-991/1/index.html
Code coverage of this PR: vs. Master:

[zhanghang1989]

why make this change?

[chunhanl]

Hello,
According in test.py

gluon-cv/scripts/segmentation/test.py

Line 20 in a78965f

def parse_args():

The args defined in parse_args() no longer has args 'model-zoo'

[zhanghang1989]

Please add that back instead. Not sure who removed that.

[chunhanl]

I'm not sure whether this may have conflicts with these settings.

gluon-cv/scripts/segmentation/test.py

Lines 204 to 230 in a78965f

	model_prefix = args.model + '_' + args.backbone
	if 'pascal' in args.dataset:
	model_prefix += '_voc'
	withQuantization = True if (args.backbone in ['resnet101']) else withQuantization
	elif args.dataset == 'coco':
	model_prefix += '_coco'
	withQuantization = True if (args.backbone in ['resnet101']) else withQuantization
	elif args.dataset == 'ade20k':
	model_prefix += '_ade'
	elif args.dataset == 'citys':
	model_prefix += '_citys'
	else:
	raise ValueError('Unsupported dataset {} used'.format(args.dataset))
	if args.ngpus > 0:
	withQuantization = False
	if withQuantization and args.quantized:
	model_prefix += '_int8'
	if not args.deploy:
	if args.calibration:
	args.pretrained = True
	# create network
	if args.pretrained:
	model = get_model(model_prefix, pretrained=True)
	model.collect_params().reset_ctx(ctx=args.ctx)

[zhanghang1989]

batch_intersection_union is supposed to work for a batch with 4D.

[chunhanl]

OK I'll try to modify from the dataset

[chunhanl]

python test.py --dataset ade20k --pretrained --model fcn --backbone resnet50 --eval

python test.py --dataset pascal_voc --pretrained --model fcn --backbone resnet101 --eval

[mli]

Job PR-991-2 is done.
Docs are uploaded to http://gluon-vision-staging.s3-website-us-west-2.amazonaws.com/PR-991/2/index.html
Code coverage of this PR: vs. Master:

[zhanghang1989]

This is incorrect. The output of gluoncv segmentation network is always a list