refine doc

open-mmlab · Mar 14, 2023 · c5c1499 · c5c1499
1 parent 0e81472
commit c5c1499
Show file tree

Hide file tree

Showing 4 changed files with 17 additions and 17 deletions.
diff --git a/configs/pidnet/README.md b/configs/pidnet/README.md
@@ -19,7 +19,7 @@ Two-branch network architecture has shown its efficiency and effectiveness for r
 <!-- [IMAGE] -->
 
 <div align=center>
-<img src="https://raw.githubusercontent.com/XuJiacong/PIDNet/main/figs/pidnet.jpg" width="400"/>
+<img src="https://raw.githubusercontent.com/XuJiacong/PIDNet/main/figs/pidnet.jpg" width="800"/>
 </div>
 
 ## Results and models
@@ -28,9 +28,9 @@ Two-branch network architecture has shown its efficiency and effectiveness for r
 
 | Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) | config                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                 |
 | ------ | -------- | --------- | ------- | -------- | -------------- | ----- | ------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| PIDNet | PIDNet-S | 1024x1024 | 120000  | 3466     | 80.82          | 78.74 | 80.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
-| PIDNet | PIDNet-M | 1024x1024 | 120000  | 5260     | 71.98          | 80.22 | 82.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
-| PIDNet | PIDNet-L | 1024x1024 | 120000  | 5970     | 60.06          | 80.89 | 82.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
+| PIDNet | PIDNet-S | 1024x1024 | 120000  | 3.38     | 80.82          | 78.74 | 80.87         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
+| PIDNet | PIDNet-M | 1024x1024 | 120000  | 5.14     | 71.98          | 80.22 | 82.05         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
+| PIDNet | PIDNet-L | 1024x1024 | 120000  | 5.83     | 60.06          | 80.89 | 82.37         | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
 
 ## Notes
 

diff --git a/configs/pidnet/pidnet.yml b/configs/pidnet/pidnet.yml
@@ -26,7 +26,7 @@ Models:
       batch size: 1
       mode: FP32
       resolution: (1024,1024)
-    Training Memory (GB): 3466.0
+    Training Memory (GB): 3.38
   Results:
   - Task: Semantic Segmentation
     Dataset: Cityscapes
@@ -48,7 +48,7 @@ Models:
       batch size: 1
       mode: FP32
       resolution: (1024,1024)
-    Training Memory (GB): 5260.0
+    Training Memory (GB): 5.14
   Results:
   - Task: Semantic Segmentation
     Dataset: Cityscapes
@@ -70,7 +70,7 @@ Models:
       batch size: 1
       mode: FP32
       resolution: (1024,1024)
-    Training Memory (GB): 5970.0
+    Training Memory (GB): 5.83
   Results:
   - Task: Semantic Segmentation
     Dataset: Cityscapes

diff --git a/mmseg/models/losses/boundary_loss.py b/mmseg/models/losses/boundary_loss.py
@@ -32,12 +32,12 @@ def __init__(self,
 
     def forward(self, bd_pre: Tensor, bd_gt: Tensor) -> Tensor:
         """Forward function.
-            Args:
-                bd_pre (Tensor): Predictions of the boundary head.
-                bd_gt (Tensor): Ground truth of the boundary.
+        Args:
+            bd_pre (Tensor): Predictions of the boundary head.
+            bd_gt (Tensor): Ground truth of the boundary.
 
-            Returns:
-                Tensor: Loss tensor.
+        Returns:
+            Tensor: Loss tensor.
         """
         log_p = bd_pre.permute(0, 2, 3, 1).contiguous().view(1, -1)
         target_t = bd_gt.view(1, -1).float()

diff --git a/mmseg/models/losses/ohem_cross_entropy_loss.py b/mmseg/models/losses/ohem_cross_entropy_loss.py
@@ -51,12 +51,12 @@ def __init__(self,
 
     def forward(self, score: Tensor, target: Tensor) -> Tensor:
         """Forward function.
-            Args:
-                score (Tensor): Predictions of the segmentation head.
-                target (Tensor): Ground truth of the image.
+        Args:
+            score (Tensor): Predictions of the segmentation head.
+            target (Tensor): Ground truth of the image.
 
-            Returns:
-                Tensor: Loss tensor.
+        Returns:
+            Tensor: Loss tensor.
         """
         # score: (N, C, H, W)
         pred = F.softmax(score, dim=1)