Update README.md
Browse files
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 |

|
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 |
-
|
66 |
<pre>
|
67 |
π CVRPDataset/
|
68 |
ββπ 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 |
-
|
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 |
-
|
112 |
data_root = 'CVRPDataset/'
|
113 |
```
|
114 |
-
|
115 |
-
|
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 |

|
39 |
|
40 |
***Train and Test***
|
|
|
62 |
```bash
|
63 |
python run/split_dataset.py
|
64 |
```
|
65 |
+
now, the structure looks like:
|
66 |
<pre>
|
67 |
π CVRPDataset/
|
68 |
ββπ 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:
|