update the anaalysis code and change some parameter

README.md

@@ -49,6 +49,35 @@ $ python -c "import JackFramework as jf; print(jf.version())"
 
 you can find the template project in: https://github.com/Archaic-Atom/FameworkTemplate
 
+**Related Arguments for training or testing process**
+|   Args        |   Type  |      Description                 | Default         |
+|:-------------:|:-------:|:--------------------------------:|:---------------:|
+| mode          |  [str]  |         train or test            |  train          |
+| gpu           |  [int]  |        the number of gpus        |    2            |
+| auto_save_num |  [int]  | the number of interval save      |    1            |
+| dataloaderNum |  [int]  |  the number of dataloders        |    8            |
+| pretrain      |  [bool] |    is a new traning process>     |  False          |
+| ip            |  [str]  | used for distributed training    | 127.0.0.1       |
+| port          |  [str]  | used for distributed training    | 8086            |
+| dist          |  [bool] | distributed training (DDP)       | True            |
+| trainListPath |  [str]  | the list for training or testing | ./Datasets/*.csv|
+| valListPath   |  [str]  | the list for validate process    | ./Datasets/*.csv|
+| outputDir     |  [str]  | the folder for log file          | ./Result/       |
+| modelDir      |  [str]  | the folder for saving model      | ./Checkpoint/   |
+| resultImgDir  |  [str]  | the folder for output            | ./ResultImg/    |
+| log           |  [str]  | the folder for tensorboard       | ./log/          |
+| sampleNum     |  [int]  | the number of sample for data    | 1               |
+| batchSize     |  [int]  | batch size                       | 4               |
+| lr            |  [float]| leanring rate                    | 0.001           |
+| maxEpochs     |  [int]  | training epoch                   | 30              |
+| imgWidth      |  [int]  | the croped width                 | 512             |
+| imgHeight     |  [int]  | the croped height                | 256             |
+| imgNum        |  [int]  | the number of images for tranin  | 35354           |
+| valImgNum     |  [int]  | the number of images for val     | 200             |
+| modelName     |  [str]  | the model's name                 | NLCA-Net        |
+| dataset       |  [str]  | the dataset's name               | SceneFlow       |
+
+
 **5) Clean the project (if you want to clean generating files)**
 ```
 $ ./clean.sh

Source/JackFramework/Evaluation/accuracy.py

@@ -40,18 +40,18 @@ def r2_score(res: tensor, gt: tensor) -> tensor:
         gt_mean = torch.mean(gt)
         ss_tot = torch.sum((gt - gt_mean) ** 2)
         ss_res = torch.sum((gt - res) ** 2)
-        r2 = 1 - ss_res / ss_tot
+        r2 = ss_res / ss_tot
         return r2
 
     @staticmethod
-    def rmse_score(res: tensor, gt: tensor) -> tensor:
-        return torch.sqrt(torch.mean((res - gt)**2))
+    def rmspe_score(res: tensor, gt: tensor) -> tensor:
+        return torch.sqrt(torch.mean((res - gt)**2 / gt))
 
 
 def debug_main():
     pred = torch.rand(10, 600)
     gt = torch.rand(10, 600)
-    out = Accuracy.rmse_score(pred, gt)
+    out = Accuracy.r2_score(pred, gt)
     print(out)
 
 

Source/JackFramework/NN/layer.py

@@ -52,6 +52,25 @@ def norm_act_layer(layer: list, out_channels: int,
 
         return layer
 
+    @staticmethod
+    def conv_1d_layer(in_channels: int, out_channels: int, kernel_size: int,
+                      stride: int = 1, padding: int = 1, dilation: int = 1,
+                      bias: bool = False, norm: bool = True,
+                      act: bool = True) -> object:
+        layer = [
+            Ops.conv_1d(
+                in_channels,
+                out_channels,
+                kernel_size,
+                stride,
+                padding,
+                dilation,
+                bias=bias,
+            )
+        ]
+        layer = Layer.norm_act_layer(layer, out_channels, norm, act)
+        return nn.Sequential(*layer)
+
     @staticmethod
     def conv_2d_layer(in_channels: int, out_channels: int, kernel_size: int,
                       stride: int = 1, padding: int = 1, dilation: int = 1,

Source/JackFramework/NN/ops.py

@@ -15,6 +15,15 @@ def __new__(cls, *args: str, **kwargs: str) -> object:
             cls.__OPS = object.__new__(cls)
         return cls.__OPS
 
+    @staticmethod
+    def conv_1d(in_channels: int, out_channels: int, kernel_size: int,
+                stride: int = 1, padding: int = 0, dilation: int = 1,
+                groups: int = 1, bias: bool = False,
+                padding_mode: str = 'circular') -> object:
+        return nn.Conv1d(in_channels, out_channels, kernel_size,
+                         stride, padding, dilation, groups,
+                         bias, padding_mode)
+
     @staticmethod
     def conv_2d(in_channels: int, out_channels: int, kernel_size: int,
                 stride: int = 1, padding: int = 0, dilation: int = 1,