feat: Add CNN model

inference.py

@@ -5,6 +5,7 @@
 import torch.nn.functional as F
 from torch.utils.data import Dataset, DataLoader
 from model.model import HousePriceModel, TransformerRegressor
+from model.model_v2 import HousePriceModel_CNN
 from dataloader import  HousePriceTestDataset, min_max_denormalize, z_score_denormalize
 import platform
 
@@ -41,8 +42,9 @@ def inference():
     # Load Model
     model_path = 'model.pth'  # Update with the path of your trained model file
     input_dim = len(normalize_columns.keys())
-    model = HousePriceModel(input_dim)
-    model = TransformerRegressor(input_dim, 4, 6)
+    # model = HousePriceModel(input_dim)
+    # model = TransformerRegressor(input_dim, 4, 6)
+    model = HousePriceModel_CNN(input_dim)
     if gpu:
         model = model.cuda()
     else:

model/model_v2.py

@@ -0,0 +1,52 @@
+import torch
+# from torch.utils.data import DataLoader
+import torch.nn as nn
+# from torch.autograd import Variable
+# import matplotlib.pyplot as plt
+# import torchvision
+# from dataloader import getDataset
+# import os
+# import numpy as np
+# from tqdm import tqdm
+# import math
+
+
+
+class HousePriceModel_CNN(nn.Module):
+    def __init__(self, input_dim):
+        super(HousePriceModel_CNN, self).__init__()
+        self.input_dim = input_dim
+        self.conv1 = nn.Sequential(
+            nn.Conv2d(in_channels = self.input_dim, out_channels = 32, kernel_size = 3, stride = 1, padding = 1,),
+            nn.LeakyReLU(0.1),
+            nn.Conv2d(in_channels = 32, out_channels = 32, kernel_size = 9, stride = 1, padding = 6),# stride = 1, padding = (kernel_size-1)/2 = (5-1)/2
+            nn.LeakyReLU(0.1),
+            nn.Conv2d(in_channels = 32, out_channels = 64, kernel_size = 9, stride = 1, padding = 5,),
+            nn.LeakyReLU(0.1),
+            nn.Conv2d(in_channels = 64, out_channels = 64, kernel_size = (3,3), stride = 1, padding = 1,),
+            nn.LeakyReLU(0.1),
+            nn.Conv2d(in_channels = 64, out_channels =32, kernel_size = (1,1), stride = 1, padding = 0,),
+            nn.LeakyReLU(0.1),
+            nn.Conv2d(in_channels = 32, out_channels = 32, kernel_size = 5, stride = 1, padding = 0,),
+            nn.LeakyReLU(0.1),
+            # nn.Conv2d(in_channels = 32, out_channels = 64, kernel_size = (3,3), stride = 1, padding = 0,),
+            # nn.LeakyReLU(0.1),
+            # nn.Conv2d(in_channels = 64, out_channels = 32, kernel_size = (1,1), stride = 1, padding = 0,),
+            # nn.LeakyReLU(0.1),
+            # nn.Conv2d(in_channels = 32, out_channels = 64, kernel_size = (3,3), stride = 1, padding = 0,),
+            # nn.LeakyReLU(0.1),
+            # nn.Conv2d(in_channels = 64, out_channels = 32, kernel_size = (1,1), stride = 1, padding = 0,),
+            # nn.LeakyReLU(0.1),
+            nn.Conv2d(in_channels = 32, out_channels = 16, kernel_size = (1,1), stride = 1, padding = 0,),
+            nn.Conv2d(in_channels = 16, out_channels = 1, kernel_size = (1,1), stride = 1, padding = 0,),
+        )
+        # self.sigmoid = nn.Sigmoid()
+
+
+    def forward(self, x):
+        x = torch.reshape(x,(-1,self.input_dim,1,1))
+        x = self.conv1(x)
+        x = torch.reshape(x,(-1,1,1,1))
+        # print(x.shape)
+
+        return x

train.py

@@ -3,6 +3,7 @@
 from torch.utils.data import Dataset, DataLoader
 from sklearn.preprocessing import StandardScaler
 from model.model import HousePriceModel, TransformerRegressor
+from model.model_v2 import HousePriceModel_CNN
 from dataloader import HousePriceTrainDataset
 import platform
 
@@ -20,7 +21,7 @@ def main():
     '移轉層次': 'min-max',
     '總樓層數': 'min-max',
     '屋齡': 'min-max',
-    # '建物面積': 'min-max',
+    '建物面積': 'min-max',
     '車位面積': 'min-max',
     '車位個數': 'min-max',
     '橫坐標': 'min-max', #z-score
@@ -44,7 +45,8 @@ def main():
     print(input_dim)
     # Initialize model
     # model = HousePriceModel(input_dim)
-    model = TransformerRegressor(input_dim, 4, 11)
+    # model = TransformerRegressor(input_dim, 4, 6)
+    model = HousePriceModel_CNN(input_dim)
 
     if gpu:
         model = model.cuda()
@@ -58,6 +60,8 @@ def main():
     # Training loop
     for epoch in range(epochs):
         for batch in train_loader:
+            # print(batch['features'].shape)
+            # print(batch['target'].shape)
             if gpu:
                 data = batch['features'].cuda()
                 targets = batch['target'].cuda()