update

README copy.md

@@ -0,0 +1,13 @@
+---
+title: Snnetv2 Semantic Segmentation
+emoji: 🐨
+colorFrom: green
+colorTo: red
+sdk: gradio
+sdk_version: 4.14.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,251 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from argparse import ArgumentParser
+
+import cv2
+from mmengine.model.utils import revert_sync_batchnorm
+
+from mmseg.apis import inference_model, init_model
+from mmseg.apis.inference import show_result_pyplot
+import torch
+import time
+import gradio as gr
+import plotly.express as px
+import json
+
+def main():
+    parser = ArgumentParser()
+    parser.add_argument('--config', default='configs/snnet/setr_naive_512x512_160k_b16_ade20k_deit_3_s_l_224_snnetv2.py', help='Config file')
+    parser.add_argument('--checkpoint', help='Checkpoint file', default='setr_naive_512x512_160k_b16_ade20k_snnetv2_deit3_s_l_lora_16_iter_160000.pth')
+    # parser.add_argument('--video', help='Video file or webcam id')
+
+    parser.add_argument(
+        '--device', default='cuda:0', help='Device used for inference')
+    parser.add_argument(
+        '--palette',
+        default='cityscapes',
+        help='Color palette used for segmentation map')
+    parser.add_argument(
+        '--show', action='store_true', help='Whether to show draw result')
+    parser.add_argument(
+        '--show-wait-time', default=1, type=int, help='Wait time after imshow')
+    parser.add_argument(
+        '--output-file', default=None, type=str, help='Output video file path')
+    parser.add_argument(
+        '--output-fourcc',
+        default='MJPG',
+        type=str,
+        help='Fourcc of the output video')
+    parser.add_argument(
+        '--output-fps', default=30, type=int, help='FPS of the output video')
+    parser.add_argument(
+        '--output-height',
+        default=-1,
+        type=int,
+        help='Frame height of the output video')
+    parser.add_argument(
+        '--output-width',
+        default=-1,
+        type=int,
+        help='Frame width of the output video')
+    parser.add_argument(
+        '--opacity',
+        type=float,
+        default=0.5,
+        help='Opacity of painted segmentation map. In (0, 1] range.')
+    args = parser.parse_args()
+
+    # build the model from a config file and a checkpoint file
+    model = init_model(args.config, args.checkpoint, device=args.device)
+    if args.device == 'cpu':
+        model = revert_sync_batchnorm(model)
+
+    from mmseg.models.backbones.snnet import get_stitch_configs_bidirection
+    stitch_configs_info, _, _, anchor_ids, sl_ids, ls_ids, lsl_ids, sls_ids = get_stitch_configs_bidirection([12, 24])
+
+    stitch_configs_info = {i: cfg for i, cfg in enumerate(stitch_configs_info)}
+
+
+    with open('./model_flops/snnet_flops_setr_naive_512x512_160k_b16_ade20k_deit_3_s_l_224_snnetv2.json', 'r') as f:
+        flops_params = json.load(f)
+
+    with open('./results/eval_single_scale_20230507_235400.json', 'r') as f:
+        results = json.load(f)
+
+    config_ids = list(results.keys())
+    flops_res = {}
+    eval_res = {}
+    total_data = {}
+    for i, cfg_id in enumerate(config_ids):
+        flops = flops_params[cfg_id]
+        miou_res = results[cfg_id]['metric']['mIoU'] * 100
+        eval_res[int(cfg_id)] = miou_res
+        flops_res[int(cfg_id)] = flops / 1e9
+        total_data[int(cfg_id)] = [flops // 1e9, miou_res]
+
+
+    def visualize_stitch_pos(stitch_id):
+        if stitch_id == 13:
+            # 13 is equivalent to 0
+            stitch_id = 0
+
+        names = [f'ID {key}' for key in flops_res.keys()]
+
+        fig = px.scatter(x=flops_res.values(), y=eval_res.values(), hover_name=names)
+        fig.update_layout(
+            title=f"SN-Netv2 - Stitch ID - {stitch_id}",
+            title_x=0.5,
+            xaxis_title="GFLOPs",
+            yaxis_title="mIoU",
+            font=dict(
+                family="Courier New, monospace",
+                size=18,
+                color="RebeccaPurple"
+            ),
+            legend=dict(
+                yanchor="bottom",
+                y=0.99,
+                xanchor="left",
+                x=0.01),
+        )
+        # continent, DarkSlateGrey
+        fig.update_traces(marker=dict(size=10,
+                                      line=dict(width=2)),
+                          selector=dict(mode='markers'))
+
+        fig.add_scatter(x=[flops_res[stitch_id]], y=[eval_res[stitch_id]], mode='markers', marker=dict(size=15), name='Current Stitch')
+        return fig
+
+
+    def segment_video(video, stitch_id):
+
+        if stitch_id == 13:
+            # 13 is equivalent to 0
+            stitch_id = 0
+
+        model.backbone.reset_stitch_id(stitch_id)
+        output_video_path = './temp_video.avi'
+        cap = cv2.VideoCapture(video)
+        assert (cap.isOpened())
+        input_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
+        input_width = cap.get(cv2.CAP_PROP_FRAME_WIDTH)
+        input_fps = cap.get(cv2.CAP_PROP_FPS)
+
+
+        fourcc = cv2.VideoWriter_fourcc(*args.output_fourcc)
+        output_fps = args.output_fps if args.output_fps > 0 else input_fps
+        output_height = args.output_height if args.output_height > 0 else int(
+            input_height)
+        output_width = args.output_width if args.output_width > 0 else int(
+            input_width)
+        writer = cv2.VideoWriter(output_video_path, fourcc, output_fps,
+                                 (output_width, output_height), True)
+
+        try:
+            while True:
+                start_time = time.time()
+                flag, frame = cap.read()
+                if not flag:
+                    break
+
+                # test a single image
+                result = inference_model(model, frame)
+
+                # blend raw image and prediction
+                draw_img = show_result_pyplot(model, frame, result,
+                                              show=False,
+                                              with_labels=False,
+                                              )
+
+                if draw_img.shape[0] != output_height or draw_img.shape[
+                    1] != output_width:
+                    draw_img = cv2.resize(draw_img,
+                                          (output_width, output_height))
+                writer.write(draw_img)
+        finally:
+            if writer:
+                writer.release()
+            cap.release()
+
+        fig = visualize_stitch_pos(stitch_id)
+        
+        return output_video_path, fig
+
+    def segment_image(image, stitch_id):
+        if stitch_id == 13:
+            # 13 is equivalent to 0
+            stitch_id = 0
+
+        model.backbone.reset_stitch_id(stitch_id)
+        result = inference_model(model, image)
+        draw_img = show_result_pyplot(model, image, result,
+                                      show=False,
+                                      with_labels=True,
+                                      )
+        fig = visualize_stitch_pos(stitch_id)
+        return draw_img, fig
+
+
+
+    with gr.Blocks() as image_demo:
+        with gr.Row():
+            with gr.Column():
+                image_input = gr.Image(label='Input Image')
+                stitch_slider = gr.Slider(minimum=0, maximum=134, step=1, label="Stitch ID")
+                with gr.Row():
+                    clear_button = gr.ClearButton()
+                    submit_button = gr.Button()
+
+            with gr.Column():
+                image_output = gr.Image(label='Segmentation Results')
+                stitch_plot = gr.Plot(label='Stitch Position')
+
+            submit_button.click(
+                fn=segment_image,
+                inputs=[image_input, stitch_slider],
+                outputs=[image_output, stitch_plot],
+            )
+
+            stitch_slider.change(
+                fn=visualize_stitch_pos,
+                inputs=[stitch_slider],
+                outputs=[stitch_plot],
+                show_progress=False
+            )
+
+            clear_button.click(
+                lambda: [None, 0, None, None],
+                outputs=[image_input, stitch_slider, image_output, stitch_plot],
+            )
+
+        gr.Examples(
+            [
+                ['./demo_1.jpg', 0],
+                ['./demo_2.jpg', 1],
+                ['./demo_3.jpg', 93],
+                ['./demo_4.jpg', 3],
+            ],
+            inputs=[
+                image_input,
+                stitch_slider
+            ],
+            outputs=[
+                image_input,
+                stitch_plot
+            ],
+        )
+
+    with gr.Blocks() as demo:
+        with gr.Column():
+            gr.HTML("""
+                <h1 align="center" style=" display: flex; flex-direction: row; justify-content: center; font-size: 25pt; ">Stitched ViTs are Flexible Vision Backbones</h1>
+                <div align="center"> <img align="center" src='file/gradio_banner.png' width="70%"> </div>
+                <h3 align="center" >This is the classification demo page of SN-Netv2, an flexible vision backbone that allows for 100+ runtime speed and performance trade-offs. You can also run this gradio demo on your local GPUs at <a href="https://github.com/ziplab/SN-Netv2">https://github.com/ziplab/SN-Netv2</a>, Paper link: <a href="https://arxiv.org/abs/2307.00154">https://arxiv.org/abs/2307.00154</a>.</h3>
+                """)
+        tabbed_page = gr.TabbedInterface([image_demo,], ['Image'])
+
+
+    demo.launch(allowed_paths=['./'])
+
+
+if __name__ == '__main__':
+    main()

configs/_base_/datasets/ade20k.py

@@ -0,0 +1,68 @@
+# dataset settings
+dataset_type = 'ADE20KDataset'
+data_root = 'data/ade/ADEChallengeData2016'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=(2048, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/training', seg_map_path='annotations/training'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/ade20k_640x640.py

@@ -0,0 +1,68 @@
+# dataset settings
+dataset_type = 'ADE20KDataset'
+data_root = 'data/ade/ADEChallengeData2016'
+crop_size = (640, 640)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=(2560, 640),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2560, 640), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/training', seg_map_path='annotations/training'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/bdd100k.py

@@ -0,0 +1,70 @@
+# dataset settings
+dataset_type = 'BDD100KDataset'
+data_root = 'data/bdd100k/'
+
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/10k/train',
+            seg_map_path='labels/sem_seg/masks/train'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/10k/val',
+            seg_map_path='labels/sem_seg/masks/val'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/chase_db1.py

@@ -0,0 +1,75 @@
+# dataset settings
+dataset_type = 'ChaseDB1Dataset'
+data_root = 'data/CHASE_DB1'
+img_scale = (960, 999)
+crop_size = (128, 128)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type='RepeatDataset',
+        times=40000,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            data_prefix=dict(
+                img_path='images/training',
+                seg_map_path='annotations/training'),
+            pipeline=train_pipeline)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes.py

@@ -0,0 +1,67 @@
+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='leftImg8bit/train', seg_map_path='gtFine/train'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='leftImg8bit/val', seg_map_path='gtFine/val'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_1024x1024.py

@@ -0,0 +1,29 @@
+_base_ = './cityscapes.py'
+crop_size = (1024, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_768x768.py

@@ -0,0 +1,29 @@
+_base_ = './cityscapes.py'
+crop_size = (768, 768)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2049, 1025),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2049, 1025), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_769x769.py

@@ -0,0 +1,29 @@
+_base_ = './cityscapes.py'
+crop_size = (769, 769)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2049, 1025),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2049, 1025), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_832x832.py

@@ -0,0 +1,29 @@
+_base_ = './cityscapes.py'
+crop_size = (832, 832)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/coco-stuff10k.py

@@ -0,0 +1,69 @@
+# dataset settings
+dataset_type = 'COCOStuffDataset'
+data_root = 'data/coco_stuff10k'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=(2048, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        reduce_zero_label=True,
+        data_prefix=dict(
+            img_path='images/train2014', seg_map_path='annotations/train2014'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        reduce_zero_label=True,
+        data_prefix=dict(
+            img_path='images/test2014', seg_map_path='annotations/test2014'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/coco-stuff164k.py

@@ -0,0 +1,67 @@
+# dataset settings
+dataset_type = 'COCOStuffDataset'
+data_root = 'data/coco_stuff164k'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/train2017', seg_map_path='annotations/train2017'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/val2017', seg_map_path='annotations/val2017'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/drive.py

@@ -0,0 +1,73 @@
+# dataset settings
+dataset_type = 'DRIVEDataset'
+data_root = 'data/DRIVE'
+img_scale = (584, 565)
+crop_size = (64, 64)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type='RepeatDataset',
+        times=40000,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            data_prefix=dict(
+                img_path='images/training',
+                seg_map_path='annotations/training'),
+            pipeline=train_pipeline)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
+test_evaluator = val_evaluator

configs/_base_/datasets/hrf.py

@@ -0,0 +1,73 @@
+# dataset settings
+dataset_type = 'HRFDataset'
+data_root = 'data/HRF'
+img_scale = (2336, 3504)
+crop_size = (256, 256)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type='RepeatDataset',
+        times=40000,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            data_prefix=dict(
+                img_path='images/training',
+                seg_map_path='annotations/training'),
+            pipeline=train_pipeline)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
+test_evaluator = val_evaluator

configs/_base_/datasets/isaid.py

@@ -0,0 +1,73 @@
+# dataset settings
+dataset_type = 'iSAIDDataset'
+data_root = 'data/iSAID'
+"""
+This crop_size setting is followed by the implementation of
+`PointFlow: Flowing Semantics Through Points for Aerial Image
+Segmentation <https://arxiv.org/pdf/2103.06564.pdf>`_.
+"""
+
+crop_size = (896, 896)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(896, 896),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(896, 896), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/levir_256x256.py

@@ -0,0 +1,59 @@
+# dataset settings
+dataset_type = 'LEVIRCDDataset'
+data_root = r'data/LEVIRCD'
+
+albu_train_transforms = [
+    dict(type='RandomBrightnessContrast', p=0.2),
+    dict(type='HorizontalFlip', p=0.5),
+    dict(type='VerticalFlip', p=0.5)
+]
+
+train_pipeline = [
+    dict(type='LoadMultipleRSImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(type='Albu', transforms=albu_train_transforms),
+    dict(type='ConcatCDInput'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadMultipleRSImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(type='ConcatCDInput'),
+    dict(type='PackSegInputs')
+]
+
+tta_pipeline = [
+    dict(type='LoadMultipleRSImageFromFile'),
+    dict(
+        type='TestTimeAug',
+        transforms=[[dict(type='LoadAnnotations')],
+                    [dict(type='ConcatCDInput')],
+                    [dict(type='PackSegInputs')]])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='train/A',
+            img_path2='train/B',
+            seg_map_path='train/label'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='test/A', img_path2='test/B', seg_map_path='test/label'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/loveda.py

@@ -0,0 +1,66 @@
+# dataset settings
+dataset_type = 'LoveDADataset'
+data_root = 'data/loveDA'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=(2048, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(1024, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/mapillary_v1.py

@@ -0,0 +1,68 @@
+# dataset settings
+dataset_type = 'MapillaryDataset_v1'
+data_root = 'data/mapillary/'
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='training/images', seg_map_path='training/v1.2/labels'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='validation/images',
+            seg_map_path='validation/v1.2/labels'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/mapillary_v1_65.py

@@ -0,0 +1,37 @@
+# dataset settings
+_base_ = './mapillary_v1.py'
+metainfo = dict(
+    classes=('Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail', 'Barrier',
+             'Wall', 'Bike Lane', 'Crosswalk - Plain', 'Curb Cut', 'Parking',
+             'Pedestrian Area', 'Rail Track', 'Road', 'Service Lane',
+             'Sidewalk', 'Bridge', 'Building', 'Tunnel', 'Person', 'Bicyclist',
+             'Motorcyclist', 'Other Rider', 'Lane Marking - Crosswalk',
+             'Lane Marking - General', 'Mountain', 'Sand', 'Sky', 'Snow',
+             'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench', 'Bike Rack',
+             'Billboard', 'Catch Basin', 'CCTV Camera', 'Fire Hydrant',
+             'Junction Box', 'Mailbox', 'Manhole', 'Phone Booth', 'Pothole',
+             'Street Light', 'Pole', 'Traffic Sign Frame', 'Utility Pole',
+             'Traffic Light', 'Traffic Sign (Back)', 'Traffic Sign (Front)',
+             'Trash Can', 'Bicycle', 'Boat', 'Bus', 'Car', 'Caravan',
+             'Motorcycle', 'On Rails', 'Other Vehicle', 'Trailer', 'Truck',
+             'Wheeled Slow', 'Car Mount', 'Ego Vehicle'),
+    palette=[[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
+             [180, 165, 180], [90, 120, 150], [102, 102, 156], [128, 64, 255],
+             [140, 140, 200], [170, 170, 170], [250, 170, 160], [96, 96, 96],
+             [230, 150, 140], [128, 64, 128], [110, 110, 110], [244, 35, 232],
+             [150, 100, 100], [70, 70, 70], [150, 120, 90], [220, 20, 60],
+             [255, 0, 0], [255, 0, 100], [255, 0, 200], [200, 128, 128],
+             [255, 255, 255], [64, 170, 64], [230, 160, 50], [70, 130, 180],
+             [190, 255, 255], [152, 251, 152], [107, 142, 35], [0, 170, 30],
+             [255, 255, 128], [250, 0, 30], [100, 140, 180], [220, 220, 220],
+             [220, 128, 128], [222, 40, 40], [100, 170, 30], [40, 40, 40],
+             [33, 33, 33], [100, 128, 160], [142, 0, 0], [70, 100, 150],
+             [210, 170, 100], [153, 153, 153], [128, 128, 128], [0, 0, 80],
+             [250, 170, 30], [192, 192, 192], [220, 220, 0], [140, 140, 20],
+             [119, 11, 32], [150, 0, 255], [0, 60, 100], [0, 0, 142],
+             [0, 0, 90], [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+             [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10, 10]])
+
+train_dataloader = dict(dataset=dict(metainfo=metainfo))
+val_dataloader = dict(dataset=dict(metainfo=metainfo))
+test_dataloader = val_dataloader

configs/_base_/datasets/mapillary_v2.py

@@ -0,0 +1,68 @@
+# dataset settings
+dataset_type = 'MapillaryDataset_v2'
+data_root = 'data/mapillary/'
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 1024),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='training/images', seg_map_path='training/v2.0/labels'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='validation/images',
+            seg_map_path='validation/v2.0/labels'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/nyu.py

@@ -0,0 +1,67 @@
+# dataset settings
+dataset_type = 'NYUDataset'
+data_root = 'data/nyu'
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3),
+    dict(type='RandomDepthMix', prob=0.25),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='RandomCrop', crop_size=(480, 480)),
+    dict(
+        type='Albu',
+        transforms=[
+            dict(type='RandomBrightnessContrast'),
+            dict(type='RandomGamma'),
+            dict(type='HueSaturationValue'),
+        ]),
+    dict(
+        type='PackSegInputs',
+        meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape',
+                   'pad_shape', 'scale_factor', 'flip', 'flip_direction',
+                   'category_id')),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2000, 480), keep_ratio=True),
+    dict(dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3)),
+    dict(
+        type='PackSegInputs',
+        meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape',
+                   'pad_shape', 'scale_factor', 'flip', 'flip_direction',
+                   'category_id'))
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=8,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/train', depth_map_path='annotations/train'),
+        pipeline=train_pipeline))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        test_mode=True,
+        data_prefix=dict(
+            img_path='images/test', depth_map_path='annotations/test'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='DepthMetric',
+    min_depth_eval=0.001,
+    max_depth_eval=10.0,
+    crop_type='nyu_crop')
+test_evaluator = val_evaluator

configs/_base_/datasets/nyu_512x512.py

@@ -0,0 +1,72 @@
+# dataset settings
+dataset_type = 'NYUDataset'
+data_root = 'data/nyu'
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3),
+    dict(type='RandomDepthMix', prob=0.25),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='RandomResize',
+        scale=(768, 512),
+        ratio_range=(0.8, 1.5),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(512, 512)),
+    dict(
+        type='Albu',
+        transforms=[
+            dict(type='RandomBrightnessContrast'),
+            dict(type='RandomGamma'),
+            dict(type='HueSaturationValue'),
+        ]),
+    dict(
+        type='PackSegInputs',
+        meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape',
+                   'pad_shape', 'scale_factor', 'flip', 'flip_direction',
+                   'category_id')),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    dict(dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3)),
+    dict(
+        type='PackSegInputs',
+        meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape',
+                   'pad_shape', 'scale_factor', 'flip', 'flip_direction',
+                   'category_id'))
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=8,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/train', depth_map_path='annotations/train'),
+        pipeline=train_pipeline))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        test_mode=True,
+        data_prefix=dict(
+            img_path='images/test', depth_map_path='annotations/test'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='DepthMetric',
+    min_depth_eval=0.001,
+    max_depth_eval=10.0,
+    crop_type='nyu_crop')
+test_evaluator = val_evaluator

configs/_base_/datasets/pascal_context.py

@@ -0,0 +1,56 @@
+# dataset settings
+dataset_type = 'PascalContextDataset'
+data_root = 'data/VOCdevkit/VOC2010/'
+
+img_scale = (520, 520)
+crop_size = (480, 480)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='JPEGImages', seg_map_path='SegmentationClassContext'),
+        ann_file='ImageSets/SegmentationContext/train.txt',
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='JPEGImages', seg_map_path='SegmentationClassContext'),
+        ann_file='ImageSets/SegmentationContext/val.txt',
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/pascal_context_59.py

@@ -0,0 +1,72 @@
+# dataset settings
+dataset_type = 'PascalContextDataset59'
+data_root = 'data/VOCdevkit/VOC2010/'
+
+img_scale = (520, 520)
+crop_size = (480, 480)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='JPEGImages', seg_map_path='SegmentationClassContext'),
+        ann_file='ImageSets/SegmentationContext/train.txt',
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='JPEGImages', seg_map_path='SegmentationClassContext'),
+        ann_file='ImageSets/SegmentationContext/val.txt',
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/pascal_voc12.py

@@ -0,0 +1,69 @@
+# dataset settings
+dataset_type = 'PascalVOCDataset'
+data_root = 'data/VOCdevkit/VOC2012'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='JPEGImages', seg_map_path='SegmentationClass'),
+        ann_file='ImageSets/Segmentation/train.txt',
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='JPEGImages', seg_map_path='SegmentationClass'),
+        ann_file='ImageSets/Segmentation/val.txt',
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/pascal_voc12_aug.py

@@ -0,0 +1,81 @@
+# dataset settings
+dataset_type = 'PascalVOCDataset'
+data_root = 'data/VOCdevkit/VOC2012'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Pad', size=crop_size),
+    dict(type='PackSegInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+dataset_train = dict(
+    type=dataset_type,
+    data_root=data_root,
+    data_prefix=dict(img_path='JPEGImages', seg_map_path='SegmentationClass'),
+    ann_file='ImageSets/Segmentation/train.txt',
+    pipeline=train_pipeline)
+
+dataset_aug = dict(
+    type=dataset_type,
+    data_root=data_root,
+    data_prefix=dict(
+        img_path='JPEGImages', seg_map_path='SegmentationClassAug'),
+    ann_file='ImageSets/Segmentation/aug.txt',
+    pipeline=train_pipeline)
+
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(type='ConcatDataset', datasets=[dataset_train, dataset_aug]))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='JPEGImages', seg_map_path='SegmentationClass'),
+        ann_file='ImageSets/Segmentation/val.txt',
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/potsdam.py

@@ -0,0 +1,66 @@
+# dataset settings
+dataset_type = 'PotsdamDataset'
+data_root = 'data/potsdam'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=(512, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(512, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/datasets/refuge.py

@@ -0,0 +1,90 @@
+# dataset settings
+dataset_type = 'REFUGEDataset'
+data_root = 'data/REFUGE'
+train_img_scale = (2056, 2124)
+val_img_scale = (1634, 1634)
+test_img_scale = (1634, 1634)
+crop_size = (512, 512)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=False),
+    dict(
+        type='RandomResize',
+        scale=train_img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+val_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=val_img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=False),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=test_img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=False),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/training', seg_map_path='annotations/training'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=val_pipeline))
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/test', seg_map_path='annotations/test'),
+        pipeline=val_pipeline))
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
+test_evaluator = val_evaluator

configs/_base_/datasets/stare.py

@@ -0,0 +1,73 @@
+# dataset settings
+dataset_type = 'STAREDataset'
+data_root = 'data/STARE'
+img_scale = (605, 700)
+crop_size = (128, 128)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=img_scale,
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type='RepeatDataset',
+        times=40000,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            data_prefix=dict(
+                img_path='images/training',
+                seg_map_path='annotations/training'),
+            pipeline=train_pipeline)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='images/validation',
+            seg_map_path='annotations/validation'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
+test_evaluator = val_evaluator

configs/_base_/datasets/synapse.py

@@ -0,0 +1,41 @@
+dataset_type = 'SynapseDataset'
+data_root = 'data/synapse/'
+img_scale = (224, 224)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    dict(type='RandomRotFlip', rotate_prob=0.5, flip_prob=0.5, degree=20),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+train_dataloader = dict(
+    batch_size=6,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
+test_evaluator = val_evaluator

configs/_base_/datasets/vaihingen.py

@@ -0,0 +1,66 @@
+# dataset settings
+dataset_type = 'ISPRSDataset'
+data_root = 'data/vaihingen'
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(
+        type='RandomResize',
+        scale=(512, 512),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(512, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale_factor=r, keep_ratio=True)
+                for r in img_ratios
+            ],
+            [
+                dict(type='RandomFlip', prob=0., direction='horizontal'),
+                dict(type='RandomFlip', prob=1., direction='horizontal')
+            ], [dict(type='LoadAnnotations')], [dict(type='PackSegInputs')]
+        ])
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            img_path='img_dir/train', seg_map_path='ann_dir/train'),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = val_evaluator

configs/_base_/default_runtime.py

@@ -0,0 +1,15 @@
+default_scope = 'mmseg'
+env_cfg = dict(
+    cudnn_benchmark=True,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'),
+)
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='SegLocalVisualizer', vis_backends=vis_backends, name='visualizer')
+log_processor = dict(by_epoch=False)
+log_level = 'INFO'
+load_from = None
+resume = False
+
+tta_model = dict(type='SegTTAModel')

configs/_base_/models/ann_r50-d8.py

@@ -0,0 +1,54 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='ANNHead',
+        in_channels=[1024, 2048],
+        in_index=[2, 3],
+        channels=512,
+        project_channels=256,
+        query_scales=(1, ),
+        key_pool_scales=(1, 3, 6, 8),
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/apcnet_r50-d8.py

@@ -0,0 +1,52 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='APCHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        pool_scales=(1, 2, 3, 6),
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/bisenetv1_r18-d32.py

@@ -0,0 +1,76 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    backbone=dict(
+        type='BiSeNetV1',
+        in_channels=3,
+        context_channels=(128, 256, 512),
+        spatial_channels=(64, 64, 64, 128),
+        out_indices=(0, 1, 2),
+        out_channels=256,
+        backbone_cfg=dict(
+            type='ResNet',
+            in_channels=3,
+            depth=18,
+            num_stages=4,
+            out_indices=(0, 1, 2, 3),
+            dilations=(1, 1, 1, 1),
+            strides=(1, 2, 2, 2),
+            norm_cfg=norm_cfg,
+            norm_eval=False,
+            style='pytorch',
+            contract_dilation=True),
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        init_cfg=None),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=256,
+        in_index=0,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=[
+        dict(
+            type='FCNHead',
+            in_channels=128,
+            channels=64,
+            num_convs=1,
+            num_classes=19,
+            in_index=1,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+        dict(
+            type='FCNHead',
+            in_channels=128,
+            channels=64,
+            num_convs=1,
+            num_classes=19,
+            in_index=2,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    ],
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/bisenetv2.py

@@ -0,0 +1,88 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained=None,
+    backbone=dict(
+        type='BiSeNetV2',
+        detail_channels=(64, 64, 128),
+        semantic_channels=(16, 32, 64, 128),
+        semantic_expansion_ratio=6,
+        bga_channels=128,
+        out_indices=(0, 1, 2, 3, 4),
+        init_cfg=None,
+        align_corners=False),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=128,
+        in_index=0,
+        channels=1024,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=[
+        dict(
+            type='FCNHead',
+            in_channels=16,
+            channels=16,
+            num_convs=2,
+            num_classes=19,
+            in_index=1,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+        dict(
+            type='FCNHead',
+            in_channels=32,
+            channels=64,
+            num_convs=2,
+            num_classes=19,
+            in_index=2,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+        dict(
+            type='FCNHead',
+            in_channels=64,
+            channels=256,
+            num_convs=2,
+            num_classes=19,
+            in_index=3,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+        dict(
+            type='FCNHead',
+            in_channels=128,
+            channels=1024,
+            num_convs=2,
+            num_classes=19,
+            in_index=4,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    ],
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/ccnet_r50-d8.py

@@ -0,0 +1,52 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='CCHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        recurrence=2,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/cgnet.py

@@ -0,0 +1,43 @@
+# model settings
+norm_cfg = dict(type='SyncBN', eps=1e-03, requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[72.39239876, 82.90891754, 73.15835921],
+    std=[1, 1, 1],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    backbone=dict(
+        type='CGNet',
+        norm_cfg=norm_cfg,
+        in_channels=3,
+        num_channels=(32, 64, 128),
+        num_blocks=(3, 21),
+        dilations=(2, 4),
+        reductions=(8, 16)),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=256,
+        in_index=2,
+        channels=256,
+        num_convs=0,
+        concat_input=False,
+        dropout_ratio=0,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        loss_decode=dict(
+            type='CrossEntropyLoss',
+            use_sigmoid=False,
+            loss_weight=1.0,
+            class_weight=[
+                2.5959933, 6.7415504, 3.5354059, 9.8663225, 9.690899, 9.369352,
+                10.289121, 9.953208, 4.3097677, 9.490387, 7.674431, 9.396905,
+                10.347791, 6.3927646, 10.226669, 10.241062, 10.280587,
+                10.396974, 10.055647
+            ])),
+    # model training and testing settings
+    train_cfg=dict(sampler=None),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/danet_r50-d8.py

@@ -0,0 +1,52 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='DAHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        pam_channels=64,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/deeplabv3_r50-d8.py

@@ -0,0 +1,52 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='ASPPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dilations=(1, 12, 24, 36),
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/deeplabv3_unet_s5-d16.py

@@ -0,0 +1,58 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained=None,
+    backbone=dict(
+        type='UNet',
+        in_channels=3,
+        base_channels=64,
+        num_stages=5,
+        strides=(1, 1, 1, 1, 1),
+        enc_num_convs=(2, 2, 2, 2, 2),
+        dec_num_convs=(2, 2, 2, 2),
+        downsamples=(True, True, True, True),
+        enc_dilations=(1, 1, 1, 1, 1),
+        dec_dilations=(1, 1, 1, 1),
+        with_cp=False,
+        conv_cfg=None,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='ReLU'),
+        upsample_cfg=dict(type='InterpConv'),
+        norm_eval=False),
+    decode_head=dict(
+        type='ASPPHead',
+        in_channels=64,
+        in_index=4,
+        channels=16,
+        dilations=(1, 12, 24, 36),
+        dropout_ratio=0.1,
+        num_classes=2,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=128,
+        in_index=3,
+        channels=64,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=2,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='slide', crop_size=256, stride=170))

configs/_base_/models/deeplabv3plus_r50-d8.py

@@ -0,0 +1,54 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='DepthwiseSeparableASPPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dilations=(1, 12, 24, 36),
+        c1_in_channels=256,
+        c1_channels=48,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/dmnet_r50-d8.py

@@ -0,0 +1,52 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='DMHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        filter_sizes=(1, 3, 5, 7),
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/dnl_r50-d8.py

@@ -0,0 +1,54 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='DNLHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dropout_ratio=0.1,
+        reduction=2,
+        use_scale=True,
+        mode='embedded_gaussian',
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/dpt_vit-b16.py

@@ -0,0 +1,39 @@
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='pretrain/vit-b16_p16_224-80ecf9dd.pth', # noqa
+    backbone=dict(
+        type='VisionTransformer',
+        img_size=224,
+        embed_dims=768,
+        num_layers=12,
+        num_heads=12,
+        out_indices=(2, 5, 8, 11),
+        final_norm=False,
+        with_cls_token=True,
+        output_cls_token=True),
+    decode_head=dict(
+        type='DPTHead',
+        in_channels=(768, 768, 768, 768),
+        channels=256,
+        embed_dims=768,
+        post_process_channels=[96, 192, 384, 768],
+        num_classes=150,
+        readout_type='project',
+        input_transform='multiple_select',
+        in_index=(0, 1, 2, 3),
+        norm_cfg=norm_cfg,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=None,
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))  # yapf: disable

configs/_base_/models/emanet_r50-d8.py

@@ -0,0 +1,55 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='EMAHead',
+        in_channels=2048,
+        in_index=3,
+        channels=256,
+        ema_channels=512,
+        num_bases=64,
+        num_stages=3,
+        momentum=0.1,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/encnet_r50-d8.py

@@ -0,0 +1,56 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='EncHead',
+        in_channels=[512, 1024, 2048],
+        in_index=(1, 2, 3),
+        channels=512,
+        num_codes=32,
+        use_se_loss=True,
+        add_lateral=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+        loss_se_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.2)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/erfnet_fcn.py

@@ -0,0 +1,40 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    pretrained=None,
+    backbone=dict(
+        type='ERFNet',
+        in_channels=3,
+        enc_downsample_channels=(16, 64, 128),
+        enc_stage_non_bottlenecks=(5, 8),
+        enc_non_bottleneck_dilations=(2, 4, 8, 16),
+        enc_non_bottleneck_channels=(64, 128),
+        dec_upsample_channels=(64, 16),
+        dec_stages_non_bottleneck=(2, 2),
+        dec_non_bottleneck_channels=(64, 16),
+        dropout_ratio=0.1,
+        init_cfg=None),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=16,
+        channels=128,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

configs/_base_/models/fast_scnn.py

@@ -0,0 +1,65 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255)
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=data_preprocessor,
+    backbone=dict(
+        type='FastSCNN',
+        downsample_dw_channels=(32, 48),
+        global_in_channels=64,
+        global_block_channels=(64, 96, 128),
+        global_block_strides=(2, 2, 1),
+        global_out_channels=128,
+        higher_in_channels=64,
+        lower_in_channels=128,
+        fusion_out_channels=128,
+        out_indices=(0, 1, 2),
+        norm_cfg=norm_cfg,
+        align_corners=False),
+    decode_head=dict(
+        type='DepthwiseSeparableFCNHead',
+        in_channels=128,
+        channels=128,
+        concat_input=False,
+        num_classes=19,
+        in_index=-1,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1)),
+    auxiliary_head=[
+        dict(
+            type='FCNHead',
+            in_channels=128,
+            channels=32,
+            num_convs=1,
+            num_classes=19,
+            in_index=-2,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.4)),
+        dict(
+            type='FCNHead',
+            in_channels=64,
+            channels=32,
+            num_convs=1,
+            num_classes=19,
+            in_index=-3,
+            norm_cfg=norm_cfg,
+            concat_input=False,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.4)),
+    ],
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))