Adding Cityscapes config file for SOLOv2 training

configs/solov2/solov2_r50_fpn_8gpu_1x_cityscapes.py

@@ -0,0 +1,133 @@
+# model settings
+model = dict(
+    type='SOLOv2',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3), # C2, C3, C4, C5
+        frozen_stages=1,
+        style='pytorch'),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=0,
+        num_outs=5),
+    bbox_head=dict(
+        type='SOLOv2Head',
+        num_classes=9,
+        in_channels=256,
+        stacked_convs=4,
+        seg_feat_channels=512,
+        strides=[8, 8, 16, 32, 32],
+        scale_ranges=((1, 96), (48, 192), (96, 384), (192, 768), (384, 2048)),
+        sigma=0.2,
+        num_grids=[100, 80, 74, 66, 42],
+        ins_out_channels=256,
+        loss_ins=dict(
+            type='DiceLoss',
+            use_sigmoid=True,
+            loss_weight=3.0),
+        loss_cate=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0)),
+    mask_feat_head=dict(
+            type='MaskFeatHead',
+            in_channels=256,
+            out_channels=128,
+            start_level=0,
+            end_level=3,
+            num_classes=256,
+            norm_cfg=dict(type='GN', num_groups=32, requires_grad=True))
+    )
+# training and testing settings
+train_cfg = dict()
+test_cfg = dict(
+    nms_pre=500,
+    score_thr=0.1,
+    mask_thr=0.5,
+    update_thr=0.05,
+    kernel='gaussian',  # gaussian/linear
+    sigma=2.0,
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', img_scale=[(2048,1024)], keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048,1024),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    imgs_per_gpu=3,
+    workers_per_gpu=5,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_train.json',
+        img_prefix=data_root + 'train/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_val.json',
+        img_prefix=data_root + 'val/',
+        pipeline=train_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_test.json',
+        img_prefix=data_root + 'test/',
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.001, 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=20,
+    warmup_ratio=0.01,
+    step=[9, 11])
+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 = 30
+device_ids = range(8)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/SOLOv2_CS'
+load_from = ''
+resume_from = None
+workflow = [('train', 1),('val',1)]
+