CVRPDataset commited on
Commit
ba746ac
Β·
verified Β·
1 Parent(s): 24881d7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -33,8 +33,8 @@ pip install "mmdet>=3.0.0rc4"
33
  python app.py
34
  ```
35
  ##### The UI :
36
- 1.Users can upload an image or use a sample image at β‘ .Then, they can select one of four models at β‘‘. We recommend **Mask2Former**. After that, click *Run*.
37
- 2.We provide two forms of segmentation results for download at β‘’.
38
  ![alt text](img/app.png)
39
 
40
  ***Train and Test***
@@ -62,7 +62,7 @@ Here is an example if you want to make own dataset.
62
  ```bash
63
  python run/split_dataset.py
64
  ```
65
- now, the structure looks like:
66
  <pre>
67
  πŸ“ CVRPDataset/
68
  β”œβ”€πŸ“ img_dir/
@@ -100,7 +100,7 @@ If you want to register your own dataset,
100
  β‘‘ Register dataset class in `mmseg/datasets/CVRP.py'
101
  ```python
102
  class CVRPDataset(BaseSegDataset):
103
- METAINFO = {
104
  'classes':['background','panicle'],
105
  'palette':[[127,127,127],[200,0,0]]
106
  }
@@ -108,11 +108,11 @@ If you want to register your own dataset,
108
 
109
  β‘’ Modify pipeline of data process in `config/_base_/CVRP_pipeline.py`
110
  ```python
111
- dataset_type = 'CVRPDataset'
112
  data_root = 'CVRPDataset/'
113
  ```
114
- you'll need to specify the paths for the train and evalution data directories.
115
- ```python
116
  # train_dataloader:
117
  data_prefix=dict(img_path='img_dir/train', seg_map_path='ann_dir/train')
118
  # val_dataloader:
 
33
  python app.py
34
  ```
35
  ##### The UI :
36
+ 1. Users can upload an image or use a sample image at β‘ .Then, they can select one of four models at β‘‘. We recommend **Mask2Former**. After that, click *Run*.
37
+ 2. We provide two forms of segmentation results for download at β‘’.
38
  ![alt text](img/app.png)
39
 
40
  ***Train and Test***
 
62
  ```bash
63
  python run/split_dataset.py
64
  ```
65
+ now, the structure looks like:
66
  <pre>
67
  πŸ“ CVRPDataset/
68
  β”œβ”€πŸ“ img_dir/
 
100
  β‘‘ Register dataset class in `mmseg/datasets/CVRP.py'
101
  ```python
102
  class CVRPDataset(BaseSegDataset):
103
+ METAINFO = {
104
  'classes':['background','panicle'],
105
  'palette':[[127,127,127],[200,0,0]]
106
  }
 
108
 
109
  β‘’ Modify pipeline of data process in `config/_base_/CVRP_pipeline.py`
110
  ```python
111
+ dataset_type = 'CVRPDataset'
112
  data_root = 'CVRPDataset/'
113
  ```
114
+ you'll need to specify the paths for the train and evalution data directories.
115
+ ```python
116
  # train_dataloader:
117
  data_prefix=dict(img_path='img_dir/train', seg_map_path='ann_dir/train')
118
  # val_dataloader: