🚀
If it helps you, click a star!
⭐
Update log
- 2020.12.10 Project structure adjustment, the previous code has been deleted, the adjustment will be re-uploaded code
- 2021.04.09 Re-upload the code, "V1 Commit"
- 2021.04.22 update torch distributed training
- Ongoing update .....
1. Display (Cityscapes)
- Using model DDRNet 1525 test sets, official MIOU =78.4069%
Average results
|
Class results1
|
Class results2
|
Class results3
|
- Comparison of the original and predicted images
origin
|
label
|
predict
|
2. Install
pip install -r requirements.txt
Experimental environment:
- Ubuntu 16.04 Nvidia-Cards >= 1
- python==3.6.5
- See Dependency Installation Package for details in requirement.txt
3. Model
All the modeling is done in builders/model_builder.py
- FCN
- FCN_ResNet
- SegNet
- UNet
- BiSeNet
- BiSeNetV2
- PSPNet
- DeepLabv3_plus
- HRNet
- DDRNet
| Model | Backbone | Val mIoU | Test mIoU | Imagenet Pretrain | Pretrained Model |
|---|---|---|---|---|---|
| PSPNet | ResNet 50 | 76.54% | - | √ | PSPNet |
| DeeplabV3+ | ResNet 50 | 77.78% | - | √ | DeeplabV3+ |
| DDRNet23_slim | - | DDRNet23_slim_imagenet | |||
| DDRNet23 | - | DDRNet23_imagenet | |||
| DDRNet39 | - | 79.63% | - | DDRNet39_imagenet | DDRNet39 |
| Updating more model....... |
4. Data preprocessing
This project enables you to expose data sets: Cityscapes、ISPRS
The data set is uploaded later .....
Cityscapes data set preparation is shown here:
4.1 Download the dataset
Download the dataset from the link on the website, You can get *leftImg8bit.png suffix of original image under folder leftImg8bit, a) *color.png、b) *labelIds.png、c) *instanceIds.png suffix of fine labeled image under folder gtFine.
*leftImg8bit.png : the origin picture
a) *color.png : the class is encoded by its color
b) *labelIds.png : the class is encoded by its ID
c) *instanceIds.png : the class and the instance are encoded by an instance ID
4.2 Onehot encoding of label image
The real label gray scale image Onehot encoding used by the semantic segmentation task is 0-18, so the label needs to be encoded. Using scripts dataset/cityscapes/cityscapes_scripts/process_cityscapes.py to process the image and get the result *labelTrainIds.png. process_cityscapes.py usage: Modify 486 lines `Cityscapes_path'is the path to store your own data.
- Comparison of original image, color label image and gray label image (0-18)
***_leftImg8bit
|
***_gtFine_color
|
***_gtFine_labelTrainIds
|
- Local storage path display
/data/open_data/cityscapes/:
data
|--open_data
|--cityscapes
|--leftImg8bit
|--train
|--cologne
|--*******
|--val
|--*******
|--test
|--*******
|--gtFine
|--train
|--cologne
|--*******
|--val
|--*******
|--test
|--*******
4.3 Generate image path
- Generate a txt containing the image path
Use scriptdataset/generate_txt.pyto generate the pathtxtfile containing the original image and labels. A total of 3txtfiles will be generated:cityscapes_train_list.txt、cityscapes_val_list.txt、cityscapes_test_list.txt, and copy the three files to the dataset root directory.
data
|--open_data
|--cityscapes
|--cityscapes_train_list.txt
|--cityscapes_val_list.txt
|--cityscapes_test_list.txt
|--leftImg8bit
|--train
|--cologne
|--*******
|--val
|--*******
|--test
|--*******
|--gtFine
|--train
|--cologne
|--*******
|--val
|--*******
|--test
|--*******
- The contents of the
txtare shown as follows:
leftImg8bit/train/cologne/cologne_000000_000019_leftImg8bit.png gtFine/train/cologne/cologne_000000_000019_gtFine_labelTrainIds.png
leftImg8bit/train/cologne/cologne_000001_000019_leftImg8bit.png gtFine/train/cologne/cologne_000001_000019_gtFine_labelTrainIds.png
..............
- The format of the
txtare shown as follows:
origin image path + the separator '\t' + label path + the separator '\n'
TODO.....
5. How to train
sh train.sh
5.1 Parameters
python -m torch.distributed.launch --nproc_per_node=2 \
train.py --model PSPNet_res50 --out_stride 8 \
--max_epochs 200 --val_epochs 20 --batch_size 4 --lr 0.01 --optim sgd --loss ProbOhemCrossEntropy2d \
--base_size 768 --crop_size 768 --tile_hw_size 768,768 \
--root '/data/open_data' --dataset cityscapes --gpus_id 1,2
6. How to validate
sh predict.sh
36 Jan 01, 2023
8 Jan 11, 2022
0 Dec 17, 2021
4 Mar 01, 2022
90 Dec 12, 2022
152 Dec 27, 2022
341 Dec 29, 2022
3 Mar 16, 2022
36 Dec 01, 2022
1 Feb 01, 2022
0 Dec 01, 2021
6.4k Dec 31, 2022
1 Oct 24, 2021
126 Dec 30, 2022
4.6k Jan 09, 2023
2 Jan 08, 2023
4 Apr 28, 2022
1.5k Jan 02, 2023
1.2k Dec 21, 2022
287 Jan 04, 2023