add ade20k news & mmseg support

README.md

@@ -5,7 +5,9 @@
 - The PyTroch 0.4.1 version is available [here](https://github.com/HRNet/HRNet-Semantic-Segmentation/tree/master).
 
 ## News
-- [2020/07] Our paper is accepted by ECCV 2020: [Object-Contextual Representations for Semantic Segmentation](https://arxiv.org/pdf/1909.11065.pdf). Notably, the reseachers from Nvidia set a new state-of-the-art performance on Cityscapes leaderboard: [85.4%](https://www.cityscapes-dataset.com/method-details/?submissionID=7836) via combining our HRNet + OCR with a new [hierarchical mult-scale attention scheme](https://arxiv.org/abs/2005.10821). 
+- [2020/08/16] [MMSegmentation](https://github.com/open-mmlab/mmsegmentation) has supported our HRNet + OCR.
+- [2020/07/20] The researchers from AInnovation have achieved **Rank#1** on [ADE20K Leaderboard](http://sceneparsing.csail.mit.edu/) via training our HRNet + OCR with a semi-supervised learning scheme. More details are in their [Technical Report](https://arxiv.org/pdf/2007.10591.pdf).
+- [2020/07/09] Our paper is accepted by ECCV 2020: [Object-Contextual Representations for Semantic Segmentation](https://arxiv.org/pdf/1909.11065.pdf). Notably, the reseachers from Nvidia set a new state-of-the-art performance on Cityscapes leaderboard: [85.4%](https://www.cityscapes-dataset.com/method-details/?submissionID=7836) via combining our HRNet + OCR with a new [hierarchical mult-scale attention scheme](https://arxiv.org/abs/2005.10821). 
 - [2020/03/13] Our paper is accepted by TPAMI: [Deep High-Resolution Representation Learning for Visual Recognition](https://arxiv.org/pdf/1908.07919.pdf).
 - HRNet + OCR + SegFix: Rank \#1 (84.5) in [Cityscapes leaderboard](https://www.cityscapes-dataset.com/benchmarks/). OCR: object contextual represenations [pdf](https://arxiv.org/pdf/1909.11065.pdf). ***HRNet + OCR is reproduced [here](https://github.com/HRNet/HRNet-Semantic-Segmentation/tree/HRNet-OCR)***.
 - Thanks Google and UIUC researchers. A modified HRNet combined with semantic and instance multi-scale context achieves SOTA panoptic segmentation result on the Mapillary Vista challenge. See [the paper](https://arxiv.org/pdf/1910.04751.pdf).

hubconf.py

+"""File for accessing HRNet via PyTorch Hub https://pytorch.org/hub/
+
+Usage:
+    import torch
+    model = torch.hub.load('AlexeyAB/PyTorch_YOLOv4:u5_preview', 'yolov4_pacsp_s', pretrained=True, channels=3, classes=80)
+"""
+
+dependencies = ['torch']
+import torch
+from lib.models.seg_hrnet import get_seg_model
+
+
+state_dict_url = 'https://github.com/huawei-noah/ghostnet/raw/master/pytorch/models/state_dict_93.98.pth'
+
+
+def hrnet_w48_cityscapes(pretrained=False, **kwargs):
+	  """ # This docstring shows up in hub.help()
+    HRNetW48 model pretrained on Cityscapes
+    pretrained (bool): kwargs, load pretrained weights into the model
+    """
+	  model = ghostnet(num_classes=1000, width=1.0, dropout=0.2)
+	  if pretrained:
+	  	  state_dict = torch.hub.load_state_dict_from_url(state_dict_url, progress=True)
+	  	  model.load_state_dict(state_dict)
+	  return model
\ No newline at end of file

lib/config/hrnet_config.py

+# ------------------------------------------------------------------------------
+# Copyright (c) Microsoft
+# Licensed under the MIT License.
+# Create by Bin Xiao (Bin.Xiao@microsoft.com)
+# Modified by Ke Sun (sunk@mail.ustc.edu.cn), Rainbowsecret (yuyua@microsoft.com)
+# ------------------------------------------------------------------------------
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from yacs.config import CfgNode as CN
+
+
+# configs for HRNet48
+HRNET_48 = CN()
+HRNET_48.FINAL_CONV_KERNEL = 1
+
+HRNET_48.STAGE1 = CN()
+HRNET_48.STAGE1.NUM_MODULES = 1
+HRNET_48.STAGE1.NUM_BRANCHES = 1
+HRNET_48.STAGE1.NUM_BLOCKS = [4]
+HRNET_48.STAGE1.NUM_CHANNELS = [64]
+HRNET_48.STAGE1.BLOCK = 'BOTTLENECK'
+HRNET_48.STAGE1.FUSE_METHOD = 'SUM'
+
+HRNET_48.STAGE2 = CN()
+HRNET_48.STAGE2.NUM_MODULES = 1
+HRNET_48.STAGE2.NUM_BRANCHES = 2
+HRNET_48.STAGE2.NUM_BLOCKS = [4, 4]
+HRNET_48.STAGE2.NUM_CHANNELS = [48, 96]
+HRNET_48.STAGE2.BLOCK = 'BASIC'
+HRNET_48.STAGE2.FUSE_METHOD = 'SUM'
+
+HRNET_48.STAGE3 = CN()
+HRNET_48.STAGE3.NUM_MODULES = 4
+HRNET_48.STAGE3.NUM_BRANCHES = 3
+HRNET_48.STAGE3.NUM_BLOCKS = [4, 4, 4]
+HRNET_48.STAGE3.NUM_CHANNELS = [48, 96, 192]
+HRNET_48.STAGE3.BLOCK = 'BASIC'
+HRNET_48.STAGE3.FUSE_METHOD = 'SUM'
+
+HRNET_48.STAGE4 = CN()
+HRNET_48.STAGE4.NUM_MODULES = 3
+HRNET_48.STAGE4.NUM_BRANCHES = 4
+HRNET_48.STAGE4.NUM_BLOCKS = [4, 4, 4, 4]
+HRNET_48.STAGE4.NUM_CHANNELS = [48, 96, 192, 384]
+HRNET_48.STAGE4.BLOCK = 'BASIC'
+HRNET_48.STAGE4.FUSE_METHOD = 'SUM'
+
+
+# configs for HRNet32
+HRNET_32 = CN()
+HRNET_32.FINAL_CONV_KERNEL = 1
+
+HRNET_32.STAGE1 = CN()
+HRNET_32.STAGE1.NUM_MODULES = 1
+HRNET_32.STAGE1.NUM_BRANCHES = 1
+HRNET_32.STAGE1.NUM_BLOCKS = [4]
+HRNET_32.STAGE1.NUM_CHANNELS = [64]
+HRNET_32.STAGE1.BLOCK = 'BOTTLENECK'
+HRNET_32.STAGE1.FUSE_METHOD = 'SUM'
+
+HRNET_32.STAGE2 = CN()
+HRNET_32.STAGE2.NUM_MODULES = 1
+HRNET_32.STAGE2.NUM_BRANCHES = 2
+HRNET_32.STAGE2.NUM_BLOCKS = [4, 4]
+HRNET_32.STAGE2.NUM_CHANNELS = [32, 64]
+HRNET_32.STAGE2.BLOCK = 'BASIC'
+HRNET_32.STAGE2.FUSE_METHOD = 'SUM'
+
+HRNET_32.STAGE3 = CN()
+HRNET_32.STAGE3.NUM_MODULES = 4
+HRNET_32.STAGE3.NUM_BRANCHES = 3
+HRNET_32.STAGE3.NUM_BLOCKS = [4, 4, 4]
+HRNET_32.STAGE3.NUM_CHANNELS = [32, 64, 128]
+HRNET_32.STAGE3.BLOCK = 'BASIC'
+HRNET_32.STAGE3.FUSE_METHOD = 'SUM'
+
+HRNET_32.STAGE4 = CN()
+HRNET_32.STAGE4.NUM_MODULES = 3
+HRNET_32.STAGE4.NUM_BRANCHES = 4
+HRNET_32.STAGE4.NUM_BLOCKS = [4, 4, 4, 4]
+HRNET_32.STAGE4.NUM_CHANNELS = [32, 64, 128, 256]
+HRNET_32.STAGE4.BLOCK = 'BASIC'
+HRNET_32.STAGE4.FUSE_METHOD = 'SUM'
+
+
+# configs for HRNet18
+HRNET_18 = CN()
+HRNET_18.FINAL_CONV_KERNEL = 1
+
+HRNET_18.STAGE1 = CN()
+HRNET_18.STAGE1.NUM_MODULES = 1
+HRNET_18.STAGE1.NUM_BRANCHES = 1
+HRNET_18.STAGE1.NUM_BLOCKS = [4]
+HRNET_18.STAGE1.NUM_CHANNELS = [64]
+HRNET_18.STAGE1.BLOCK = 'BOTTLENECK'
+HRNET_18.STAGE1.FUSE_METHOD = 'SUM'
+
+HRNET_18.STAGE2 = CN()
+HRNET_18.STAGE2.NUM_MODULES = 1
+HRNET_18.STAGE2.NUM_BRANCHES = 2
+HRNET_18.STAGE2.NUM_BLOCKS = [4, 4]
+HRNET_18.STAGE2.NUM_CHANNELS = [18, 36]
+HRNET_18.STAGE2.BLOCK = 'BASIC'
+HRNET_18.STAGE2.FUSE_METHOD = 'SUM'
+
+HRNET_18.STAGE3 = CN()
+HRNET_18.STAGE3.NUM_MODULES = 4
+HRNET_18.STAGE3.NUM_BRANCHES = 3
+HRNET_18.STAGE3.NUM_BLOCKS = [4, 4, 4]
+HRNET_18.STAGE3.NUM_CHANNELS = [18, 36, 72]
+HRNET_18.STAGE3.BLOCK = 'BASIC'
+HRNET_18.STAGE3.FUSE_METHOD = 'SUM'
+
+HRNET_18.STAGE4 = CN()
+HRNET_18.STAGE4.NUM_MODULES = 3
+HRNET_18.STAGE4.NUM_BRANCHES = 4
+HRNET_18.STAGE4.NUM_BLOCKS = [4, 4, 4, 4]
+HRNET_18.STAGE4.NUM_CHANNELS = [18, 36, 72, 144]
+HRNET_18.STAGE4.BLOCK = 'BASIC'
+HRNET_18.STAGE4.FUSE_METHOD = 'SUM'
+
+
+MODEL_CONFIGS = {
+    'hrnet18': HRNET_18,
+    'hrnet32': HRNET_32,
+    'hrnet48': HRNET_48,
+}
\ No newline at end of file

lib/models/seg_hrnet_ocr.py

@@ -38,6 +38,7 @@ class ModuleHelper:
     def BatchNorm2d(*args, **kwargs):
         return BatchNorm2d
 
+
 def conv3x3(in_planes, out_planes, stride=1):
     """3x3 convolution with padding"""
     return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
@@ -141,6 +142,7 @@ class _ObjectAttentionBlock(nn.Module):
 
         return context
 
+
 class ObjectAttentionBlock2D(_ObjectAttentionBlock):
     def __init__(self, 
                  in_channels, 
@@ -185,6 +187,7 @@ class SpatialOCR_Module(nn.Module):
 
         return output
 
+
 class BasicBlock(nn.Module):
     expansion = 1