# model settings
normalize = dict(type='GN', num_groups=32, frozen=False)

model = dict(
	type='MaskRCNN',
	pretrained='/nfs/project/libo_i/mmdetection/models/mask_rcnn_r50_fpn_gn_2x_20180113-86832cf2.pth',
	backbone=dict(
		type='ResNet',
		depth=50,
		num_stages=4,
		out_indices=(0, 1, 2, 3),
		frozen_stages=1,
		style='pytorch',
		normalize=normalize),
	neck=dict(
		type='FPN',
		in_channels=[256, 512, 1024, 2048],
		out_channels=256,
		num_outs=5,
		normalize=normalize),
	rpn_head=dict(
		type='RPNHead',
		in_channels=256,
		feat_channels=256,
		anchor_scales=[8],
		anchor_ratios=[0.5, 1.0, 2.0],
		anchor_strides=[4, 8, 16, 32, 64],
		target_means=[.0, .0, .0, .0],
		target_stds=[1.0, 1.0, 1.0, 1.0],
		use_sigmoid_cls=True),
	bbox_roi_extractor=dict(
		type='SingleRoIExtractor',
		roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
		out_channels=256,
		featmap_strides=[4, 8, 16, 32]),
	bbox_head=dict(
		type='ConvFCBBoxHead',
		num_shared_convs=4,
		num_shared_fcs=1,
		in_channels=256,
		conv_out_channels=256,
		fc_out_channels=1024,
		roi_feat_size=7,
		num_classes=81,
		target_means=[0., 0., 0., 0.],
		target_stds=[0.1, 0.1, 0.2, 0.2],
		reg_class_agnostic=False,
		normalize=normalize),
	mask_roi_extractor=dict(
		type='SingleRoIExtractor',
		roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
		out_channels=256,
		featmap_strides=[4, 8, 16, 32]),
	mask_head=dict(
		type='FCNMaskHead',
		num_convs=4,
		in_channels=256,
		conv_out_channels=256,
		num_classes=81,
		normalize=normalize))

# model training and testing settings
train_cfg = dict(
	rpn=dict(
		assigner=dict(
			type='MaxIoUAssigner',
			pos_iou_thr=0.7,
			neg_iou_thr=0.3,
			min_pos_iou=0.3,
			ignore_iof_thr=-1),
		sampler=dict(
			type='RandomSampler',
			num=256,
			pos_fraction=0.5,
			neg_pos_ub=-1,
			add_gt_as_proposals=False),
		allowed_border=0,
		pos_weight=-1,
		smoothl1_beta=1 / 9.0,
		debug=False),
	rcnn=dict(
		assigner=dict(
			type='MaxIoUAssigner',
			pos_iou_thr=0.5,
			neg_iou_thr=0.5,
			min_pos_iou=0.5,
			ignore_iof_thr=-1),
		sampler=dict(
			type='RandomSampler',
			num=512,
			pos_fraction=0.25,
			neg_pos_ub=-1,
			add_gt_as_proposals=True),
		mask_size=28,
		pos_weight=-1,
		debug=False))
test_cfg = dict(
	rpn=dict(
		nms_across_levels=False,
		nms_pre=2000,
		nms_post=2000,
		max_num=2000,
		nms_thr=0.7,
		min_bbox_size=0),
	rcnn=dict(
		score_thr=0.05,
		nms=dict(type='nms', iou_thr=0.5),
		max_per_img=100,
		mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = '/nfs/project/libo_i/mmdetection/data/cityscapes/'
img_norm_cfg = dict(
	mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
data = dict(
	imgs_per_gpu=2,
	workers_per_gpu=0,
	train=dict(
		type=dataset_type,
		ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_train.json',
		img_prefix=data_root + 'leftImg8bit/train/',
		img_scale=(1333, 800),
		img_norm_cfg=img_norm_cfg,
		size_divisor=32,
		flip_ratio=0.5,
		with_mask=True,
		with_crowd=True,
		with_label=True),
	val=dict(
		type=dataset_type,
		ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_val.json',
		img_prefix=data_root + 'leftImg8bit/val/',
		img_scale=(1333, 800),
		img_norm_cfg=img_norm_cfg,
		size_divisor=32,
		flip_ratio=0,
		with_mask=True,
		with_crowd=True,
		with_label=True),
	test=dict(
		type=dataset_type,
		ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_test.json',
		img_prefix=data_root + 'leftImg8bit/test/',
		img_scale=(1333, 800),
		img_norm_cfg=img_norm_cfg,
		size_divisor=32,
		flip_ratio=0,
		with_mask=False,
		with_label=False,
		test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
	policy='step',
	warmup='linear',
	warmup_iters=500,
	warmup_ratio=1.0 / 3,
	step=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
	interval=50,
	hooks=[
		dict(type='TextLoggerHook'),
		# dict(type='TensorboardLoggerHook')
	])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cityscapes_mask_rcnn_r50_fpn_gn_2x'
load_from = None
resume_from = None
workflow = [('train', 1)]