update readme.md and comments

BubblyYi · Aug 13, 2020 · 6b0e876 · 6b0e876
1 parent aaf7796
commit 6b0e876
Show file tree

Hide file tree

Showing 4 changed files with 5 additions and 3 deletions.
diff --git a/example_images/seeds_points.jpg b/example_images/seeds_points.jpg
diff --git a/ostiapoints_train_tools/ostia_train_tools.py b/ostiapoints_train_tools/ostia_train_tools.py
@@ -36,7 +36,6 @@ def get_dataset(save_num=0):
     curr_model_name = "ostiapoints_net"
     model = OstiapointsNet()
 
-    # 参数设定
     batch_size = 64
     num_workers = 16
 

diff --git a/readme.md b/readme.md
@@ -38,7 +38,7 @@ The number of output channels is equal to the number of potential directions in
 The architecture of seedspint_net and ostiapoint_net are very similar to centerline_net. The only difference is in the output layer: instead of combining classiﬁcation and regression, the ﬁnal layer only performs regression.
 ```
 
-# Preparing Environmental
+# Requirement
 ```bash
 $ pip install -r requirement.txt
 ```
@@ -153,6 +153,10 @@ The predict vessel tree is shown in the figure below
 ```
 The vessels from different seed points are spliced by breadth-first search, and then a complete single vessel is generated by depth-first search
 ```
+
+Seedpoints net will generate 200 seed points as shown in the figure below. 
+![](./example_images/seeds_points.jpg)
+It can be seen that the seed points are distributed near several coronary arteries
 # References
 
 ``` 

diff --git a/seedspoints_train_tools/seeds_trainner.py b/seedspoints_train_tools/seeds_trainner.py
@@ -77,7 +77,6 @@ def train_step(self, epoch):
 
         return train_loss / len(self.train_loader)
 
-    # 验证模型
     def val_step(self, epoch):
         self.model.eval()
         test_loss = 0.