first commit
This commit is contained in:
admin
111
Seg_All_In_One_MMSeg/configs/fcn/README.md
Normal file
111
Seg_All_In_One_MMSeg/configs/fcn/README.md
Normal file
@@ -0,0 +1,111 @@
|
||||
# FCN
|
||||
|
||||
> [Fully Convolutional Networks for Semantic Segmentation](https://arxiv.org/abs/1411.4038)
|
||||
|
||||
## Introduction
|
||||
|
||||
<!-- [ALGORITHM] -->
|
||||
|
||||
<a href="https://github.com/BVLC/caffe/wiki/Model-Zoo#fcn">Official Repo</a>
|
||||
|
||||
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11">Code Snippet</a>
|
||||
|
||||
## Abstract
|
||||
|
||||
<!-- [ABSTRACT] -->
|
||||
|
||||
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a novel architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image.
|
||||
|
||||
<!-- [IMAGE] -->
|
||||
|
||||
<div align=center>
|
||||
<img src="https://user-images.githubusercontent.com/24582831/142901525-fd0d2bf4-9a47-4143-85f5-3cee8849eaa4.png" width="70%"/>
|
||||
</div>
|
||||
|
||||
## Results and models
|
||||
|
||||
### Cityscapes
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ---------- | ---------- | --------- | ------: | -------- | -------------- | -------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | R-50-D8 | 512x1024 | 40000 | 5.7 | 4.17 | V100 | 72.25 | 73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json) |
|
||||
| FCN | R-101-D8 | 512x1024 | 40000 | 9.2 | 2.66 | V100 | 75.45 | 76.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json) |
|
||||
| FCN | R-50-D8 | 769x769 | 40000 | 6.5 | 1.80 | V100 | 71.47 | 72.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json) |
|
||||
| FCN | R-101-D8 | 769x769 | 40000 | 10.4 | 1.19 | V100 | 73.93 | 75.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json) |
|
||||
| FCN | R-18-D8 | 512x1024 | 80000 | 1.7 | 14.65 | V100 | 71.11 | 72.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes-20201225_021327.log.json) |
|
||||
| FCN | R-50-D8 | 512x1024 | 80000 | - | | V100 | 73.61 | 74.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json) |
|
||||
| FCN | R-101-D8 | 512x1024 | 80000 | - | - | V100 | 75.13 | 75.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json) |
|
||||
| FCN (FP16) | R-101-D8 | 512x1024 | 80000 | 5.37 | 8.64 | V100 | 76.80 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921.log.json) |
|
||||
| FCN | R-18-D8 | 769x769 | 80000 | 1.9 | 6.40 | V100 | 70.80 | 73.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes-20201225_021451.log.json) |
|
||||
| FCN | R-50-D8 | 769x769 | 80000 | - | - | V100 | 72.64 | 73.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json) |
|
||||
| FCN | R-101-D8 | 769x769 | 80000 | - | - | V100 | 75.52 | 76.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json) |
|
||||
| FCN | R-18b-D8 | 512x1024 | 80000 | 1.6 | 16.74 | V100 | 70.24 | 72.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes-20201225_230143.log.json) |
|
||||
| FCN | R-50b-D8 | 512x1024 | 80000 | 5.6 | 4.20 | V100 | 75.65 | 77.59 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes-20201225_094221.log.json) |
|
||||
| FCN | R-101b-D8 | 512x1024 | 80000 | 9.1 | 2.73 | V100 | 77.37 | 78.77 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes-20201226_160213.log.json) |
|
||||
| FCN | R-18b-D8 | 769x769 | 80000 | 1.7 | 6.70 | V100 | 69.66 | 72.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json) |
|
||||
| FCN | R-50b-D8 | 769x769 | 80000 | 6.3 | 1.82 | V100 | 73.83 | 76.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json) |
|
||||
| FCN | R-101b-D8 | 769x769 | 80000 | 10.3 | 1.15 | V100 | 77.02 | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json) |
|
||||
| FCN (D6) | R-50-D16 | 512x1024 | 40000 | 3.4 | 10.22 | TITAN Xp | 77.06 | 78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json) |
|
||||
| FCN (D6) | R-50-D16 | 512x1024 | 80000 | - | 10.35 | TITAN Xp | 77.27 | 78.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json) |
|
||||
| FCN (D6) | R-50-D16 | 769x769 | 40000 | 3.7 | 4.17 | TITAN Xp | 76.82 | 78.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json) |
|
||||
| FCN (D6) | R-50-D16 | 769x769 | 80000 | - | 4.15 | TITAN Xp | 77.04 | 78.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json) |
|
||||
| FCN (D6) | R-101-D16 | 512x1024 | 40000 | 4.5 | 8.04 | TITAN Xp | 77.36 | 79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json) |
|
||||
| FCN (D6) | R-101-D16 | 512x1024 | 80000 | - | 8.26 | TITAN Xp | 78.46 | 80.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json) |
|
||||
| FCN (D6) | R-101-D16 | 769x769 | 40000 | 5.0 | 3.12 | TITAN Xp | 77.28 | 78.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json) |
|
||||
| FCN (D6) | R-101-D16 | 769x769 | 80000 | - | 3.21 | TITAN Xp | 78.06 | 79.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json) |
|
||||
| FCN (D6) | R-50b-D16 | 512x1024 | 80000 | 3.2 | 10.16 | TITAN Xp | 76.99 | 79.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json) |
|
||||
| FCN (D6) | R-50b-D16 | 769x769 | 80000 | 3.6 | 4.17 | TITAN Xp | 76.86 | 78.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json) |
|
||||
| FCN (D6) | R-101b-D16 | 512x1024 | 80000 | 4.3 | 8.46 | TITAN Xp | 77.72 | 79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json) |
|
||||
| FCN (D6) | R-101b-D16 | 769x769 | 80000 | 4.8 | 3.32 | TITAN Xp | 77.34 | 78.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json) |
|
||||
|
||||
### ADE20K
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | R-50-D8 | 512x512 | 80000 | 8.5 | 23.49 | V100 | 35.94 | 37.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json) |
|
||||
| FCN | R-101-D8 | 512x512 | 80000 | 12 | 14.78 | V100 | 39.61 | 40.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.pyy) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json) |
|
||||
| FCN | R-50-D8 | 512x512 | 160000 | - | - | V100 | 36.10 | 38.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json) |
|
||||
| FCN | R-101-D8 | 512x512 | 160000 | - | - | V100 | 39.91 | 41.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
|
||||
|
||||
### Pascal VOC 2012 + Aug
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | R-50-D8 | 512x512 | 20000 | 5.7 | 23.28 | V100 | 67.08 | 69.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json) |
|
||||
| FCN | R-101-D8 | 512x512 | 20000 | 9.2 | 14.81 | V100 | 71.16 | 73.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json) |
|
||||
| FCN | R-50-D8 | 512x512 | 40000 | - | - | V100 | 66.97 | 69.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json) |
|
||||
| FCN | R-101-D8 | 512x512 | 40000 | - | - | V100 | 69.91 | 72.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json) |
|
||||
|
||||
### Pascal Context
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | R-101-D8 | 480x480 | 40000 | - | 9.93 | V100 | 44.43 | 45.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json) |
|
||||
| FCN | R-101-D8 | 480x480 | 80000 | - | - | V100 | 44.13 | 45.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json) |
|
||||
|
||||
### Pascal Context 59
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | R-101-D8 | 480x480 | 40000 | - | - | V100 | 48.42 | 50.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59-20210415_230724.log.json) |
|
||||
| FCN | R-101-D8 | 480x480 | 80000 | - | - | V100 | 49.35 | 51.38 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59-20210416_110804.log.json) |
|
||||
|
||||
Note:
|
||||
|
||||
- `FP16` means Mixed Precision (FP16) is adopted in training.
|
||||
- `FCN D6` means dilation rate of convolution operator in FCN is 6.
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@article{shelhamer2017fully,
|
||||
title={Fully convolutional networks for semantic segmentation},
|
||||
author={Shelhamer, Evan and Long, Jonathan and Darrell, Trevor},
|
||||
journal={IEEE transactions on pattern analysis and machine intelligence},
|
||||
volume={39},
|
||||
number={4},
|
||||
pages={640--651},
|
||||
year={2017},
|
||||
publisher={IEEE Trans Pattern Anal Mach Intell}
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,4 @@
|
||||
_base_ = './fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(
|
||||
pretrained='torchvision://resnet101',
|
||||
backbone=dict(type='ResNet', depth=101))
|
||||
@@ -0,0 +1,4 @@
|
||||
_base_ = './fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(
|
||||
pretrained='torchvision://resnet101',
|
||||
backbone=dict(type='ResNet', depth=101))
|
||||
@@ -0,0 +1,11 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/cityscapes.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
|
||||
]
|
||||
crop_size = (512, 1024)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
backbone=dict(dilations=(1, 1, 1, 2), strides=(1, 2, 2, 1)),
|
||||
decode_head=dict(dilation=6),
|
||||
auxiliary_head=dict(dilation=6))
|
||||
@@ -0,0 +1,13 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_40k.py'
|
||||
]
|
||||
crop_size = (769, 769)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
backbone=dict(dilations=(1, 1, 1, 2), strides=(1, 2, 2, 1)),
|
||||
decode_head=dict(align_corners=True, dilation=6),
|
||||
auxiliary_head=dict(align_corners=True, dilation=6),
|
||||
test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513)))
|
||||
@@ -0,0 +1,11 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/cityscapes.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
|
||||
]
|
||||
crop_size = (512, 1024)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
backbone=dict(dilations=(1, 1, 1, 2), strides=(1, 2, 2, 1)),
|
||||
decode_head=dict(dilation=6),
|
||||
auxiliary_head=dict(dilation=6))
|
||||
@@ -0,0 +1,13 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_80k.py'
|
||||
]
|
||||
crop_size = (769, 769)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
backbone=dict(dilations=(1, 1, 1, 2), strides=(1, 2, 2, 1)),
|
||||
decode_head=dict(align_corners=True, dilation=6),
|
||||
auxiliary_head=dict(align_corners=True, dilation=6),
|
||||
test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513)))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(pretrained='torchvision://resnet50', backbone=dict(type='ResNet'))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(pretrained='torchvision://resnet50', backbone=dict(type='ResNet'))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-40k_cityscapes-769x769.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,6 @@
|
||||
_base_ = './fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py'
|
||||
optim_wrapper = dict(
|
||||
_delete_=True,
|
||||
type='AmpOptimWrapper',
|
||||
optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
|
||||
loss_scale=512.)
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-160k_ade20k-512x512.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-20k_voc12aug-512x512.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-40k_pascal-context-480x480.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-40k_pascal-context-59-480x480.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-40k_voc12aug-512x512.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-80k_ade20k-512x512.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-40k_pascal-context-480x480.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb4-80k_pascal-context-59-480x480.py'
|
||||
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
|
||||
@@ -0,0 +1,4 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(
|
||||
pretrained='torchvision://resnet101',
|
||||
backbone=dict(type='ResNet', depth=101))
|
||||
@@ -0,0 +1,4 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(
|
||||
pretrained='torchvision://resnet101',
|
||||
backbone=dict(type='ResNet', depth=101))
|
||||
@@ -0,0 +1,9 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(
|
||||
pretrained='open-mmlab://resnet18_v1c',
|
||||
backbone=dict(depth=18),
|
||||
decode_head=dict(
|
||||
in_channels=512,
|
||||
channels=128,
|
||||
),
|
||||
auxiliary_head=dict(in_channels=256, channels=64))
|
||||
@@ -0,0 +1,9 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(
|
||||
pretrained='open-mmlab://resnet18_v1c',
|
||||
backbone=dict(depth=18),
|
||||
decode_head=dict(
|
||||
in_channels=512,
|
||||
channels=128,
|
||||
),
|
||||
auxiliary_head=dict(in_channels=256, channels=64))
|
||||
@@ -0,0 +1,9 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(
|
||||
pretrained='torchvision://resnet18',
|
||||
backbone=dict(type='ResNet', depth=18),
|
||||
decode_head=dict(
|
||||
in_channels=512,
|
||||
channels=128,
|
||||
),
|
||||
auxiliary_head=dict(in_channels=256, channels=64))
|
||||
@@ -0,0 +1,9 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(
|
||||
pretrained='torchvision://resnet18',
|
||||
backbone=dict(type='ResNet', depth=18),
|
||||
decode_head=dict(
|
||||
in_channels=512,
|
||||
channels=128,
|
||||
),
|
||||
auxiliary_head=dict(in_channels=256, channels=64))
|
||||
@@ -0,0 +1,7 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/cityscapes.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
|
||||
]
|
||||
crop_size = (512, 1024)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(data_preprocessor=data_preprocessor)
|
||||
@@ -0,0 +1,12 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_40k.py'
|
||||
]
|
||||
crop_size = (769, 769)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(align_corners=True),
|
||||
auxiliary_head=dict(align_corners=True),
|
||||
test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513)))
|
||||
@@ -0,0 +1,7 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/cityscapes.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
|
||||
]
|
||||
crop_size = (512, 1024)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(data_preprocessor=data_preprocessor)
|
||||
@@ -0,0 +1,12 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_80k.py'
|
||||
]
|
||||
crop_size = (769, 769)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(align_corners=True),
|
||||
auxiliary_head=dict(align_corners=True),
|
||||
test_cfg=dict(mode='slide', crop_size=(769, 769), stride=(513, 513)))
|
||||
@@ -0,0 +1,10 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/ade20k.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
|
||||
]
|
||||
crop_size = (512, 512)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=150),
|
||||
auxiliary_head=dict(num_classes=150))
|
||||
@@ -0,0 +1,10 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/pascal_voc12_aug.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_20k.py'
|
||||
]
|
||||
crop_size = (512, 512)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=21),
|
||||
auxiliary_head=dict(num_classes=21))
|
||||
@@ -0,0 +1,13 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/pascal_context.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
|
||||
]
|
||||
crop_size = (480, 480)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=60),
|
||||
auxiliary_head=dict(num_classes=60),
|
||||
test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
|
||||
optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
|
||||
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
|
||||
@@ -0,0 +1,14 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/pascal_context_59.py', '../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_40k.py'
|
||||
]
|
||||
crop_size = (480, 480)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=59),
|
||||
auxiliary_head=dict(num_classes=59),
|
||||
test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
|
||||
optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
|
||||
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
|
||||
@@ -0,0 +1,10 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/pascal_voc12_aug.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
|
||||
]
|
||||
crop_size = (512, 512)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=21),
|
||||
auxiliary_head=dict(num_classes=21))
|
||||
@@ -0,0 +1,10 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/ade20k.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
|
||||
]
|
||||
crop_size = (512, 512)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=150),
|
||||
auxiliary_head=dict(num_classes=150))
|
||||
@@ -0,0 +1,13 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py', '../_base_/datasets/pascal_context.py',
|
||||
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
|
||||
]
|
||||
crop_size = (480, 480)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=60),
|
||||
auxiliary_head=dict(num_classes=60),
|
||||
test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
|
||||
optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
|
||||
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
|
||||
@@ -0,0 +1,14 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/pascal_context_59.py', '../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_80k.py'
|
||||
]
|
||||
crop_size = (480, 480)
|
||||
data_preprocessor = dict(size=crop_size)
|
||||
model = dict(
|
||||
data_preprocessor=data_preprocessor,
|
||||
decode_head=dict(num_classes=59),
|
||||
auxiliary_head=dict(num_classes=59),
|
||||
test_cfg=dict(mode='slide', crop_size=(480, 480), stride=(320, 320)))
|
||||
optimizer = dict(type='SGD', lr=0.004, momentum=0.9, weight_decay=0.0001)
|
||||
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer)
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py'
|
||||
model = dict(pretrained='torchvision://resnet50', backbone=dict(type='ResNet'))
|
||||
@@ -0,0 +1,2 @@
|
||||
_base_ = './fcn_r50-d8_4xb2-80k_cityscapes-769x769.py'
|
||||
model = dict(pretrained='torchvision://resnet50', backbone=dict(type='ResNet'))
|
||||
997
Seg_All_In_One_MMSeg/configs/fcn/metafile.yaml
Normal file
997
Seg_All_In_One_MMSeg/configs/fcn/metafile.yaml
Normal file
@@ -0,0 +1,997 @@
|
||||
Collections:
|
||||
- Name: FCN
|
||||
License: Apache License 2.0
|
||||
Metadata:
|
||||
Training Data:
|
||||
- Cityscapes
|
||||
- ADE20K
|
||||
- Pascal VOC 2012 + Aug
|
||||
- Pascal Context
|
||||
- Pascal Context 59
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
README: configs/fcn/README.md
|
||||
Frameworks:
|
||||
- PyTorch
|
||||
Models:
|
||||
- Name: fcn_r50-d8_4xb2-40k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 72.25
|
||||
mIoU(ms+flip): 73.36
|
||||
Config: configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 5.7
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb2-40k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 75.45
|
||||
mIoU(ms+flip): 76.58
|
||||
Config: configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 9.2
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50-d8_4xb2-40k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 71.47
|
||||
mIoU(ms+flip): 72.54
|
||||
Config: configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 6.5
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb2-40k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 73.93
|
||||
mIoU(ms+flip): 75.14
|
||||
Config: configs/fcn/fcn_r101-d8_4xb2-40k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 10.4
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r18-d8_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 71.11
|
||||
mIoU(ms+flip): 72.91
|
||||
Config: configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-18-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 1.7
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_512x1024_80k_cityscapes/fcn_r18-d8_512x1024_80k_cityscapes-20201225_021327.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50-d8_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 73.61
|
||||
mIoU(ms+flip): 74.24
|
||||
Config: configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 75.13
|
||||
mIoU(ms+flip): 75.94
|
||||
Config: configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 76.8
|
||||
Config: configs/fcn/fcn_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
- (FP16)
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 5.37
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921-fb13e883.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_fp16_512x1024_80k_cityscapes/fcn_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230921.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r18-d8_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 70.8
|
||||
mIoU(ms+flip): 73.16
|
||||
Config: configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-18-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 1.9
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes_20201225_021451-9739d1b8.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18-d8_769x769_80k_cityscapes/fcn_r18-d8_769x769_80k_cityscapes-20201225_021451.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50-d8_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 72.64
|
||||
mIoU(ms+flip): 73.32
|
||||
Config: configs/fcn/fcn_r50-d8_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 75.52
|
||||
mIoU(ms+flip): 76.61
|
||||
Config: configs/fcn/fcn_r101-d8_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r18b-d8_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 70.24
|
||||
mIoU(ms+flip): 72.77
|
||||
Config: configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-18b-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 1.6
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes_20201225_230143-92c0f445.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_512x1024_80k_cityscapes/fcn_r18b-d8_512x1024_80k_cityscapes-20201225_230143.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50b-d8_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 75.65
|
||||
mIoU(ms+flip): 77.59
|
||||
Config: configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50b-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 5.6
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes_20201225_094221-82957416.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_512x1024_80k_cityscapes/fcn_r50b-d8_512x1024_80k_cityscapes-20201225_094221.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101b-d8_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.37
|
||||
mIoU(ms+flip): 78.77
|
||||
Config: configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101b-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 9.1
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes_20201226_160213-4543858f.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_512x1024_80k_cityscapes/fcn_r101b-d8_512x1024_80k_cityscapes-20201226_160213.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r18b-d8_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 69.66
|
||||
mIoU(ms+flip): 72.07
|
||||
Config: configs/fcn/fcn_r18b-d8_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-18b-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 1.7
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50b-d8_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 73.83
|
||||
mIoU(ms+flip): 76.6
|
||||
Config: configs/fcn/fcn_r50b-d8_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50b-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 6.3
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101b-d8_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.02
|
||||
mIoU(ms+flip): 78.67
|
||||
Config: configs/fcn/fcn_r101b-d8_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101b-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 10.3
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.06
|
||||
mIoU(ms+flip): 78.85
|
||||
Config: configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 3.4
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.27
|
||||
mIoU(ms+flip): 78.88
|
||||
Config: configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 76.82
|
||||
mIoU(ms+flip): 78.22
|
||||
Config: configs/fcn/fcn-d6_r50-d16_4xb2-40k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 3.7
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.04
|
||||
mIoU(ms+flip): 78.4
|
||||
Config: configs/fcn/fcn-d6_r50-d16_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.36
|
||||
mIoU(ms+flip): 79.18
|
||||
Config: configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 4.5
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 78.46
|
||||
mIoU(ms+flip): 80.42
|
||||
Config: configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.28
|
||||
mIoU(ms+flip): 78.95
|
||||
Config: configs/fcn/fcn-d6_r101-d16_4xb2-40k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 5.0
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 78.06
|
||||
mIoU(ms+flip): 79.58
|
||||
Config: configs/fcn/fcn-d6_r101-d16_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 76.99
|
||||
mIoU(ms+flip): 79.03
|
||||
Config: configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50b-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 3.2
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 76.86
|
||||
mIoU(ms+flip): 78.52
|
||||
Config: configs/fcn/fcn-d6_r50b-d16_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-50b-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 3.6
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.72
|
||||
mIoU(ms+flip): 79.53
|
||||
Config: configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-512x1024.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101b-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 4.3
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
Metrics:
|
||||
mIoU: 77.34
|
||||
mIoU(ms+flip): 78.91
|
||||
Config: configs/fcn/fcn-d6_r101b-d16_4xb2-80k_cityscapes-769x769.py
|
||||
Metadata:
|
||||
Training Data: Cityscapes
|
||||
Batch Size: 8
|
||||
Architecture:
|
||||
- R-101b-D16
|
||||
- FCN
|
||||
- (D6)
|
||||
Training Resources: 4x TITAN Xp GPUS
|
||||
Memory (GB): 4.8
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50-d8_4xb4-80k_ade20k-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
Metrics:
|
||||
mIoU: 35.94
|
||||
mIoU(ms+flip): 37.94
|
||||
Config: configs/fcn/fcn_r50-d8_4xb4-80k_ade20k-512x512.py
|
||||
Metadata:
|
||||
Training Data: ADE20K
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 8.5
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-80k_ade20k-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
Metrics:
|
||||
mIoU: 39.61
|
||||
mIoU(ms+flip): 40.83
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-80k_ade20k-512x512.py
|
||||
Metadata:
|
||||
Training Data: ADE20K
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 12.0
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50-d8_4xb4-160k_ade20k-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
Metrics:
|
||||
mIoU: 36.1
|
||||
mIoU(ms+flip): 38.08
|
||||
Config: configs/fcn/fcn_r50-d8_4xb4-160k_ade20k-512x512.py
|
||||
Metadata:
|
||||
Training Data: ADE20K
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-160k_ade20k-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
Metrics:
|
||||
mIoU: 39.91
|
||||
mIoU(ms+flip): 41.4
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-160k_ade20k-512x512.py
|
||||
Metadata:
|
||||
Training Data: ADE20K
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50-d8_4xb4-20k_voc12aug-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
Metrics:
|
||||
mIoU: 67.08
|
||||
mIoU(ms+flip): 69.94
|
||||
Config: configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py
|
||||
Metadata:
|
||||
Training Data: Pascal VOC 2012 + Aug
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 5.7
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-20k_voc12aug-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
Metrics:
|
||||
mIoU: 71.16
|
||||
mIoU(ms+flip): 73.57
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-20k_voc12aug-512x512.py
|
||||
Metadata:
|
||||
Training Data: Pascal VOC 2012 + Aug
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Memory (GB): 9.2
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r50-d8_4xb4-40k_voc12aug-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
Metrics:
|
||||
mIoU: 66.97
|
||||
mIoU(ms+flip): 69.04
|
||||
Config: configs/fcn/fcn_r50-d8_4xb4-40k_voc12aug-512x512.py
|
||||
Metadata:
|
||||
Training Data: Pascal VOC 2012 + Aug
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-50-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-40k_voc12aug-512x512
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
Metrics:
|
||||
mIoU: 69.91
|
||||
mIoU(ms+flip): 72.38
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-40k_voc12aug-512x512.py
|
||||
Metadata:
|
||||
Training Data: Pascal VOC 2012 + Aug
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-40k_pascal-context-480x480
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
Metrics:
|
||||
mIoU: 44.43
|
||||
mIoU(ms+flip): 45.63
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-480x480.py
|
||||
Metadata:
|
||||
Training Data: Pascal Context
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-80k_pascal-context-480x480
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
Metrics:
|
||||
mIoU: 44.13
|
||||
mIoU(ms+flip): 45.26
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-480x480.py
|
||||
Metadata:
|
||||
Training Data: Pascal Context
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-40k_pascal-context-59-480x480
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal Context 59
|
||||
Metrics:
|
||||
mIoU: 48.42
|
||||
mIoU(ms+flip): 50.4
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-40k_pascal-context-59-480x480.py
|
||||
Metadata:
|
||||
Training Data: Pascal Context 59
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59_20210415_230724-8cf83682.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context_59/fcn_r101-d8_480x480_40k_pascal_context_59-20210415_230724.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
- Name: fcn_r101-d8_4xb4-80k_pascal-context-59-480x480
|
||||
In Collection: FCN
|
||||
Results:
|
||||
Task: Semantic Segmentation
|
||||
Dataset: Pascal Context 59
|
||||
Metrics:
|
||||
mIoU: 49.35
|
||||
mIoU(ms+flip): 51.38
|
||||
Config: configs/fcn/fcn_r101-d8_4xb4-80k_pascal-context-59-480x480.py
|
||||
Metadata:
|
||||
Training Data: Pascal Context 59
|
||||
Batch Size: 16
|
||||
Architecture:
|
||||
- R-101-D8
|
||||
- FCN
|
||||
Training Resources: 4x V100 GPUS
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59_20210416_110804-9a6f2c94.pth
|
||||
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context_59/fcn_r101-d8_480x480_80k_pascal_context_59-20210416_110804.log.json
|
||||
Paper:
|
||||
Title: Fully Convolutional Networks for Semantic Segmentation
|
||||
URL: https://arxiv.org/abs/1411.4038
|
||||
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/fcn_head.py#L11
|
||||
Framework: PyTorch
|
||||
@@ -0,0 +1,112 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/my_dataset_model.py',
|
||||
'../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_40k_check_4000.py',
|
||||
]
|
||||
|
||||
norm_cfg = dict(
|
||||
type='BN',
|
||||
)
|
||||
|
||||
crop_size = (512, 1024)
|
||||
|
||||
data_preprocessor = dict(
|
||||
size=(512, 1024),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
)
|
||||
|
||||
model = dict(
|
||||
pretrained='./My_Local_Model/torchvision_012/resnet101.pth',
|
||||
backbone=dict(
|
||||
type='ResNet',
|
||||
depth=101,
|
||||
strides=(1, 2, 2, 1),
|
||||
dilations=(1, 1, 1, 2),
|
||||
),
|
||||
data_preprocessor=dict(
|
||||
size=(512, 1024),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
),
|
||||
decode_head=dict(
|
||||
dilation=6,
|
||||
channels=512,
|
||||
in_channels=2048,
|
||||
num_classes=36,
|
||||
loss_decode=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=1.0,
|
||||
),
|
||||
align_corners=False,
|
||||
),
|
||||
auxiliary_head=dict(
|
||||
dilation=6,
|
||||
channels=256,
|
||||
in_channels=1024,
|
||||
num_classes=36,
|
||||
loss_decode=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=0.4,
|
||||
),
|
||||
align_corners=False,
|
||||
),
|
||||
)
|
||||
|
||||
test_cfg = dict(
|
||||
crop_size=(512, 1024),
|
||||
)
|
||||
|
||||
optim_wrapper = dict(
|
||||
type='OptimWrapper',
|
||||
_delete_=True,
|
||||
optimizer=dict(
|
||||
type='AdamW',
|
||||
lr=0.0001,
|
||||
weight_decay=0.0005,
|
||||
),
|
||||
clip_grad=dict(
|
||||
max_norm=1,
|
||||
norm_type=2,
|
||||
),
|
||||
)
|
||||
|
||||
param_scheduler = [
|
||||
dict(
|
||||
type='LinearLR',
|
||||
start_factor=1e-06,
|
||||
by_epoch=False,
|
||||
begin=0,
|
||||
end=1500,
|
||||
),
|
||||
dict(
|
||||
type='PolyLR',
|
||||
power=0.9,
|
||||
begin=1500,
|
||||
end=40000,
|
||||
eta_min=1e-05,
|
||||
by_epoch=False,
|
||||
),
|
||||
]
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/my_dataset_model.py',
|
||||
'../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_40k_check_4000.py',
|
||||
]
|
||||
|
||||
norm_cfg = dict(
|
||||
type='BN',
|
||||
)
|
||||
|
||||
crop_size = (512, 512)
|
||||
|
||||
data_preprocessor = dict(
|
||||
size=(512, 512),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
)
|
||||
|
||||
model = dict(
|
||||
pretrained='./My_Local_Model/torchvision_012/resnet101.pth',
|
||||
backbone=dict(
|
||||
type='ResNet',
|
||||
depth=101,
|
||||
strides=(1, 2, 1, 1),
|
||||
dilations=(1, 1, 2, 4),
|
||||
),
|
||||
data_preprocessor=dict(
|
||||
size=(512, 512),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
),
|
||||
decode_head=dict(
|
||||
dilation=1,
|
||||
channels=512,
|
||||
in_channels=2048,
|
||||
num_classes=36,
|
||||
decode_head_loss_decode_dict=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=1.0,
|
||||
),
|
||||
align_corners=False,
|
||||
),
|
||||
auxiliary_head=dict(
|
||||
dilation=1,
|
||||
channels=256,
|
||||
in_channels=1024,
|
||||
num_classes=36,
|
||||
auxiliary_head_loss_decode_dict=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=0.4,
|
||||
),
|
||||
align_corners=False,
|
||||
),
|
||||
)
|
||||
|
||||
test_cfg = dict(
|
||||
crop_size=(512, 512),
|
||||
)
|
||||
|
||||
optim_wrapper = dict(
|
||||
type='OptimWrapper',
|
||||
_delete_=True,
|
||||
optimizer=dict(
|
||||
type='AdamW',
|
||||
lr=0.0001,
|
||||
weight_decay=0.0005,
|
||||
),
|
||||
clip_grad=dict(
|
||||
max_norm=1,
|
||||
norm_type=2,
|
||||
),
|
||||
)
|
||||
|
||||
param_scheduler = [
|
||||
dict(
|
||||
type='LinearLR',
|
||||
start_factor=1e-06,
|
||||
by_epoch=False,
|
||||
begin=0,
|
||||
end=1500,
|
||||
),
|
||||
dict(
|
||||
type='PolyLR',
|
||||
power=0.9,
|
||||
begin=1500,
|
||||
end=40000,
|
||||
eta_min=1e-05,
|
||||
by_epoch=False,
|
||||
),
|
||||
]
|
||||
|
||||
@@ -0,0 +1,114 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/my_dataset_model.py',
|
||||
'../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_40k_check_4000.py',
|
||||
]
|
||||
|
||||
norm_cfg = dict(
|
||||
type='BN',
|
||||
)
|
||||
|
||||
crop_size = (769, 769)
|
||||
|
||||
data_preprocessor = dict(
|
||||
size=(769, 769),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
)
|
||||
|
||||
model = dict(
|
||||
pretrained='./My_Local_Model/torchvision_012/resnet18.pth',
|
||||
backbone=dict(
|
||||
type='ResNet',
|
||||
depth=18,
|
||||
strides=(1, 2, 2, 1),
|
||||
dilations=(1, 1, 1, 2),
|
||||
),
|
||||
data_preprocessor=dict(
|
||||
size=(769, 769),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
),
|
||||
decode_head=dict(
|
||||
dilation=6,
|
||||
channels=128,
|
||||
in_channels=512,
|
||||
num_classes=36,
|
||||
loss_decode=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=1.0,
|
||||
),
|
||||
align_corners=True,
|
||||
),
|
||||
auxiliary_head=dict(
|
||||
dilation=6,
|
||||
channels=64,
|
||||
in_channels=256,
|
||||
num_classes=36,
|
||||
loss_decode=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=0.4,
|
||||
),
|
||||
align_corners=True,
|
||||
),
|
||||
)
|
||||
|
||||
test_cfg = dict(
|
||||
mode='slide',
|
||||
crop_size=(769, 769),
|
||||
stride=(512, 512),
|
||||
)
|
||||
|
||||
optim_wrapper = dict(
|
||||
type='OptimWrapper',
|
||||
_delete_=True,
|
||||
optimizer=dict(
|
||||
type='AdamW',
|
||||
lr=0.0001,
|
||||
weight_decay=0.0005,
|
||||
),
|
||||
clip_grad=dict(
|
||||
max_norm=1,
|
||||
norm_type=2,
|
||||
),
|
||||
)
|
||||
|
||||
param_scheduler = [
|
||||
dict(
|
||||
type='LinearLR',
|
||||
start_factor=1e-06,
|
||||
by_epoch=False,
|
||||
begin=0,
|
||||
end=1500,
|
||||
),
|
||||
dict(
|
||||
type='PolyLR',
|
||||
power=0.9,
|
||||
begin=1500,
|
||||
end=40000,
|
||||
eta_min=1e-05,
|
||||
by_epoch=False,
|
||||
),
|
||||
]
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
_base_ = [
|
||||
'../_base_/models/fcn_r50-d8.py',
|
||||
'../_base_/datasets/my_dataset_model.py',
|
||||
'../_base_/default_runtime.py',
|
||||
'../_base_/schedules/schedule_40k_check_4000.py',
|
||||
]
|
||||
|
||||
norm_cfg = dict(
|
||||
type='BN',
|
||||
)
|
||||
|
||||
crop_size = (512, 1024)
|
||||
|
||||
data_preprocessor = dict(
|
||||
size=(512, 1024),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
)
|
||||
|
||||
model = dict(
|
||||
pretrained='./My_Local_Model/open_mmlab/resnet50_v1c.pth',
|
||||
backbone=dict(
|
||||
type='ResNetV1c',
|
||||
depth=50,
|
||||
strides=(1, 2, 2, 1),
|
||||
dilations=(1, 1, 1, 2),
|
||||
),
|
||||
data_preprocessor=dict(
|
||||
size=(512, 1024),
|
||||
mean=[
|
||||
94.94709810464303,
|
||||
61.72942233949928,
|
||||
75.93763705236906,
|
||||
],
|
||||
std=[
|
||||
44.005506081132594,
|
||||
42.69595666984776,
|
||||
44.99354156225523,
|
||||
],
|
||||
bgr_to_rgb=False,
|
||||
),
|
||||
decode_head=dict(
|
||||
dilation=6,
|
||||
channels=512,
|
||||
in_channels=2048,
|
||||
num_classes=36,
|
||||
loss_decode=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=1.0,
|
||||
),
|
||||
align_corners=False,
|
||||
),
|
||||
auxiliary_head=dict(
|
||||
dilation=6,
|
||||
channels=256,
|
||||
in_channels=1024,
|
||||
num_classes=36,
|
||||
auxiliary_head_loss_decode=dict(
|
||||
type='DiceLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=0.4,
|
||||
),
|
||||
align_corners=False,
|
||||
),
|
||||
)
|
||||
|
||||
test_cfg = dict(
|
||||
crop_size=(512, 1024),
|
||||
)
|
||||
|
||||
optim_wrapper = dict(
|
||||
type='OptimWrapper',
|
||||
_delete_=True,
|
||||
optimizer=dict(
|
||||
type='AdamW',
|
||||
lr=0.0001,
|
||||
weight_decay=0.0005,
|
||||
),
|
||||
clip_grad=dict(
|
||||
max_norm=1,
|
||||
norm_type=2,
|
||||
),
|
||||
)
|
||||
|
||||
param_scheduler = [
|
||||
dict(
|
||||
type='LinearLR',
|
||||
start_factor=1e-06,
|
||||
by_epoch=False,
|
||||
begin=0,
|
||||
end=1500,
|
||||
),
|
||||
dict(
|
||||
type='PolyLR',
|
||||
power=0.9,
|
||||
begin=1500,
|
||||
end=40000,
|
||||
eta_min=1e-05,
|
||||
by_epoch=False,
|
||||
),
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user