20250308 Commits: K-Fold has been finish, but sampler has some question to solve

Load_process/Load_Indepentend.py

@@ -21,8 +21,8 @@ class Load_Indepentend_Data():
         self.test, self.test_label = self.get_Independent_image(Test_data_root)
         print("\ntest_labels有" + str(len(self.test_label)) + "筆資料\n")
 
-        self.validation, self.validation_label = self.get_Independent_image(Validation_data_root)
-        print("validation_labels有 " + str(len(self.validation_label)) + " 筆資料\n")
+        # self.validation, self.validation_label = self.get_Independent_image(Validation_data_root)
+        # print("validation_labels有 " + str(len(self.validation_label)) + " 筆資料\n")
 
     def get_Independent_image(self, independent_DataRoot):
         image_processing = Read_image_and_Process_image(123)

Training_Tools/PreProcess.py

@@ -0,0 +1,53 @@
+from torch.utils.data import Dataset, DataLoader, RandomSampler
+import torchvision.transforms as transforms
+import torch
+
+class ListDataset(Dataset):
+    def __init__(self, data_list, labels_list, status):
+        self.data = data_list
+        self.labels = labels_list
+        self.status = status
+
+    def __len__(self):
+        return len(self.data)
+
+    def __getitem__(self, idx):
+        sample = self.data[idx]  
+
+        if self.status:
+            from Image_Process.Image_Generator import Image_generator
+            ImageGenerator = Image_generator("", "", 12)
+            Transform = ImageGenerator.Generator_Content(5)
+            sample = Transform(sample)
+
+        label = self.labels[idx]
+        return sample, label
+
+class Training_Precesses:
+    def __init__(self, Training_Datas, Training_Labels, Testing_Datas, Testing_Labels):
+        self.Training_Datas = Training_Datas
+        self.Training_Labels = Training_Labels
+        self.Testing_Datas = Testing_Datas
+        self.Testing_Labels = Testing_Labels
+        pass
+
+    def Total_Data_Combine_To_DataLoader(self, Batch_Size):
+        Training_Dataset = self.Convert_Data_To_DataSet(self.Training_Datas, self.Training_Labels)
+        Testing_Dataset = self.Convert_Data_To_DataSet(self.Testing_Datas, self.Testing_Labels)
+
+        Training_DataLoader = DataLoader(dataset = Training_Dataset, batch_size = Batch_Size, num_workers = 0, pin_memory=True, shuffle = True)
+        Testing_DataLoader = DataLoader(dataset = Testing_Dataset, batch_size = 1, num_workers = 0, pin_memory=True, shuffle = True)
+
+        return Training_DataLoader, Testing_DataLoader
+
+    def Convert_Data_To_DataSet(self, Datas : list, Labels : list, status : bool = True):
+        seed = 42  # 設定任意整數作為種子
+        # 產生隨機種子產生器
+        generator = torch.Generator()
+        generator.manual_seed(seed)
+
+        # 創建 Dataset
+        list_dataset = ListDataset(Datas, Labels, status)
+        # sampler = RandomSampler(list_dataset, generator = generator) # 創建Sampler
+
+        return list_dataset

Training_Tools/Tools.py

@@ -1,30 +1,8 @@
 import pandas as pd
 from torch.nn import functional
 import torch
-from torch.utils.data import Dataset, DataLoader, RandomSampler
-import torchvision.transforms as transforms
 
-class ListDataset(Dataset):
-    def __init__(self, data_list, labels_list, status):
-        self.data = data_list
-        self.labels = labels_list
-        self.status = status
-
-    def __len__(self):
-        return len(self.data)
-
-    def __getitem__(self, idx):
-        sample = self.data[idx]  
-
-        if self.status:
-            from Image_Process.Image_Generator import Image_generator
-            ImageGenerator = Image_generator("", "", 12)
-            Transform = ImageGenerator.Generator_Content(5)
-            sample = Transform(sample)
-
-        label = self.labels[idx]
-        return sample, label
-    
+   
 class Tool:
     def __init__(self) -> None:
         self.__ICG_Training_Root = ""
@@ -84,8 +62,8 @@ class Tool:
     
     def Get_Save_Roots(self, choose):
         '''回傳結果為Train, test, validation
-                choose = 1 => 取ICG Label
-                else => 取Normal Label
+                choose = 1 => 取白光 Label
+                else => 取濾光 Label
 
             若choose != 1 || choose != 2 => 會回傳四個結果
         '''
@@ -106,16 +84,4 @@ class Tool:
             return self.__Comprehensive_Generator_Root
         
     def Get_OneHot_Encording_Label(self):
-        return self.__OneHot_Encording
-    
-    def Convert_Data_To_DataSet_And_Put_To_Dataloader(self, Datas : list, Labels : list, Batch_Size : int, status : bool = True):
-        seed = 42  # 設定任意整數作為種子
-        # 產生隨機種子產生器
-        generator = torch.Generator()
-        generator.manual_seed(seed)
-
-        # 創建 Dataset
-        list_dataset = ListDataset(Datas, Labels, status)
-        # sampler = RandomSampler(list_dataset, generator = generator) # 創建Sampler
-
-        return DataLoader(dataset = list_dataset, batch_size = Batch_Size, num_workers = 0, pin_memory=True, shuffle = True)
+        return self.__OneHot_Encording

experiments/Model_All_Step.py

@@ -1,6 +1,7 @@
 from tqdm import tqdm
 import torch
 from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+from sklearn.model_selection import KFold
 from torchmetrics.functional import auroc
 import torch.optim as optim
 import numpy as np
@@ -8,14 +9,14 @@ from all_models_tools.all_model_tools import call_back
 from Model_Loss.Loss import Entropy_Loss
 from merge_class.merge import merge
 from draw_tools.Grad_cam import GradCAM
+from torch.utils.data import Subset, DataLoader
 import time
 
 
 class All_Step:
-    def __init__(self, Training_Data_And_Label, Test_Data_And_Label, Validation_Data_And_Label, Model, Epoch, Number_Of_Classes, Model_Name):
-        self.Training_Data_And_Label = Training_Data_And_Label
-        self.Test_Data_And_Label = Test_Data_And_Label
-        self.Validation_Data_And_Label = Validation_Data_And_Label
+    def __init__(self, PreProcess_Classes_Data, Batch, Model, Epoch, Number_Of_Classes, Model_Name):
+        self.PreProcess_Classes_Data = PreProcess_Classes_Data
+        self.Training_DataLoader, self.Test_Dataloader = self.PreProcess_Classes_Data.Total_Data_Combine_To_DataLoader(Batch)
 
         self.Model = Model
         self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
@@ -40,6 +41,8 @@ class All_Step:
         val_accuracies = []
         Total_Epoch = 0
 
+        K_Flod = KFold(n_splits = 5, shuffle = True, random_state = 42)
+
         for epoch in range(self.Epoch): # 訓練迴圈
             self.Model.train() # 開始訓練
             running_loss = 0.0
@@ -49,94 +52,103 @@ class All_Step:
 
             # 計算每個 epoch 的起始時間
             start_time = time.time()
-            total_samples = len(self.Training_Data_And_Label)
+            total_samples = len(self.Training_DataLoader)
+            train_subset = ""
+            val_subset = ""  
 
-            epoch_iterator = tqdm(self.Training_Data_And_Label, desc=f"Epoch [{epoch}/{self.Epoch}]")
+            for fold, (train_idx, vali_idx) in enumerate( K_Flod.split(self.PreProcess_Classes_Data.Training_Datas)):
+                # Create training and validation subsets for this fold
+                train_subset = Subset(self.Training_DataLoader, train_idx)
+                val_subset = Subset(self.Training_DataLoader, vali_idx)
 
-            for inputs, labels in epoch_iterator:
-                inputs, labels = torch.as_tensor(inputs).to(self.device), torch.as_tensor(labels).to(self.device)
+                Training_Data = DataLoader(train_subset, self.Training_DataLoader.batch_size, num_workers = 0, pin_memory=True, shuffle = True)
 
-                Optimizer.zero_grad()
-                outputs = self.Model(inputs)
-                loss = criterion(outputs, labels)
-                loss.backward()
-                Optimizer.step()
-                running_loss += loss.item()
+                epoch_iterator = tqdm(Training_Data, desc=f"Epoch [{epoch}/{self.Epoch}]")
 
-                # 收集訓練預測和標籤
-                Output_Values, Output_Indexs = torch.max(outputs, dim = 1)
-                True_Indexs = np.argmax(labels.cpu().numpy(), 1)
-                
-                all_train_preds.append(Output_Indexs.cpu().numpy())
-                all_train_labels.append(True_Indexs)
-
-                processed_samples += len(inputs)
-
-                # 計算當前進度
-                progress = (processed_samples / total_samples) * 100
-                
-                # 計算經過時間和剩餘時間
-                elapsed_time = time.time() - start_time
-                iterations_per_second = processed_samples / elapsed_time if elapsed_time > 0 else 0
-                eta = (total_samples - processed_samples) / iterations_per_second if iterations_per_second > 0 else 0
-                time_str = f"{int(elapsed_time//60):02d}:{int(elapsed_time%60):02d}<{int(eta//60):02d}:{int(eta%60):02d}"
-
-                # 計算當前批次的精確度（這裡需要根據你的具體需求調整）
-                batch_accuracy = (Output_Indexs.cpu().numpy() == True_Indexs).mean()
-
-                # 更新進度條顯示
-                epoch_iterator.set_description(f"Epoch [{epoch}/{self.Epoch}]")
-                epoch_iterator.set_postfix_str(
-                    f"{processed_samples}/{total_samples} [{time_str}, {iterations_per_second:.2f}it/s, " +
-                    f"acc={batch_accuracy:.3f}, loss={loss.item():.3f}, ]"
-                )
-
-            epoch_iterator.close()
-
-            all_train_preds = Merge_Function.merge_data_main(all_train_preds, 0, len(all_train_preds))
-            all_train_labels = Merge_Function.merge_data_main(all_train_labels, 0, len(all_train_labels))
-
-            Training_Loss = running_loss / len(self.Training_Data_And_Label)
-            train_accuracy = accuracy_score(all_train_labels, all_train_preds)
-
-            train_losses.append(Training_Loss)
-            train_accuracies.append(train_accuracy)
-
-            self.Model.eval()
-            val_loss = 0.0
-            all_val_preds = []
-            all_val_labels = []
-
-            with torch.no_grad():
-                for inputs, labels in self.Validation_Data_And_Label:                    
+                for inputs, labels in epoch_iterator:
                     inputs, labels = torch.as_tensor(inputs).to(self.device), torch.as_tensor(labels).to(self.device)
 
+                    Optimizer.zero_grad()
                     outputs = self.Model(inputs)
                     loss = criterion(outputs, labels)
-                    val_loss += loss.item()
+                    loss.backward()
+                    Optimizer.step()
+                    running_loss += loss.item()
 
                     # 收集訓練預測和標籤
                     Output_Values, Output_Indexs = torch.max(outputs, dim = 1)
                     True_Indexs = np.argmax(labels.cpu().numpy(), 1)
+                    
+                    all_train_preds.append(Output_Indexs.cpu().numpy())
+                    all_train_labels.append(True_Indexs)
 
-                    all_val_preds.append(Output_Indexs.cpu().numpy())
-                    all_val_labels.append(True_Indexs)
+                    processed_samples += len(inputs)
 
-            val_loss /= len(self.Validation_Data_And_Label)
-            val_accuracy = accuracy_score(all_val_labels, all_val_preds)
+                    # 計算當前進度
+                    progress = (processed_samples / total_samples) * 100
+                    
+                    # 計算經過時間和剩餘時間
+                    elapsed_time = time.time() - start_time
+                    iterations_per_second = processed_samples / elapsed_time if elapsed_time > 0 else 0
+                    eta = (total_samples - processed_samples) / iterations_per_second if iterations_per_second > 0 else 0
+                    time_str = f"{int(elapsed_time//60):02d}:{int(elapsed_time%60):02d}<{int(eta//60):02d}:{int(eta%60):02d}"
 
-            val_losses.append(val_loss)
-            val_accuracies.append(val_accuracy)
-            # print(f"Val_loss: {val_loss:.4f}, Val_accuracy: {val_accuracy:0.2f}\n")
+                    # 計算當前批次的精確度（這裡需要根據你的具體需求調整）
+                    batch_accuracy = (Output_Indexs.cpu().numpy() == True_Indexs).mean()
 
-            early_stopping(val_loss, self.Model, model_path)
-            if early_stopping.early_stop:
-                print("Early stopping triggered. Training stopped.")
-                Total_Epoch = epoch
-                break
+                    # 更新進度條顯示
+                    epoch_iterator.set_description(f"Epoch [{epoch}/{self.Epoch}]")
+                    epoch_iterator.set_postfix_str(
+                        f"{processed_samples}/{total_samples} [{time_str}, {iterations_per_second:.2f}it/s, " +
+                        f"acc={batch_accuracy:.3f}, loss={loss.item():.3f}, ]"
+                    )
 
-            # 學習率調整
-            scheduler.step(val_loss)
+                epoch_iterator.close()
+
+                all_train_preds = Merge_Function.merge_data_main(all_train_preds, 0, len(all_train_preds))
+                all_train_labels = Merge_Function.merge_data_main(all_train_labels, 0, len(all_train_labels))
+
+                Training_Loss = running_loss / len(self.Training_DataLoader)
+                train_accuracy = accuracy_score(all_train_labels, all_train_preds)
+
+                train_losses.append(Training_Loss)
+                train_accuracies.append(train_accuracy)
+
+                self.Model.eval()
+                val_loss = 0.0
+                all_val_preds = []
+                all_val_labels = []
+
+                with torch.no_grad():
+                    for inputs, labels in val_subset:                    
+                        inputs, labels = torch.as_tensor(inputs).to(self.device), torch.as_tensor(labels).to(self.device)
+
+                        outputs = self.Model(inputs)
+                        loss = criterion(outputs, labels)
+                        val_loss += loss.item()
+
+                        # 收集訓練預測和標籤
+                        Output_Values, Output_Indexs = torch.max(outputs, dim = 1)
+                        True_Indexs = np.argmax(labels.cpu().numpy(), 1)
+
+                        all_val_preds.append(Output_Indexs.cpu().numpy())
+                        all_val_labels.append(True_Indexs)
+
+                val_loss /= len(val_subset)
+                val_accuracy = accuracy_score(all_val_labels, all_val_preds)
+
+                val_losses.append(val_loss)
+                val_accuracies.append(val_accuracy)
+                # print(f"Val_loss: {val_loss:.4f}, Val_accuracy: {val_accuracy:0.2f}\n")
+
+                early_stopping(val_loss, self.Model, model_path)
+                if early_stopping.early_stop:
+                    print("Early stopping triggered. Training stopped.")
+                    Total_Epoch = epoch
+                    break
+
+                # 學習率調整
+                scheduler.step(val_loss)
 
         return train_losses, val_losses, train_accuracies, val_accuracies, Total_Epoch
 
@@ -148,7 +160,7 @@ class All_Step:
         loss = 0.0
 
         with torch.no_grad():
-            for images, labels in self.Test_Data_And_Label:
+            for images, labels in self.Test_Dataloader:
                 images, labels = torch.tensor(images).to(self.device), torch.tensor(labels).to(self.device)
 
                 outputs = cnn_model(images)
@@ -163,13 +175,13 @@ class All_Step:
                 Predict_Label_OneHot.append(torch.tensor(outputs, dtype = torch.float32).cpu().numpy()[0])
                 True_Label_OneHot.append(torch.tensor(labels, dtype = torch.int).cpu().numpy()[0])
 
-                # 創建 GradCAM 實例
-                Layers = cnn_model.base_model.body.conv4.pointwise
-                grad_cam = GradCAM(cnn_model, target_layer="base_model")
-                # 可視化 Grad-CAM
-                grad_cam.visualize(outputs, images, target_class = 3, File_Name = counter, model_name = self.Model_Name)
+                # # 創建 GradCAM 實例
+                # Layers = cnn_model.base_model.body.conv4.pointwise
+                # grad_cam = GradCAM(cnn_model, target_layer="base_model")
+                # # 可視化 Grad-CAM
+                # grad_cam.visualize(outputs, images, target_class = 3, File_Name = counter, model_name = self.Model_Name)
 
-        loss /= len(self.Test_Data_And_Label)
+        loss /= len(self.Test_Dataloader)
 
         True_Label_OneHot = torch.tensor(True_Label_OneHot, dtype = torch.int)
         Predict_Label_OneHot = torch.tensor(Predict_Label_OneHot, dtype = torch.float32)

experiments/experiment.py

@@ -5,6 +5,7 @@ from Load_process.file_processing import Process_File
 from sklearn.metrics import confusion_matrix
 from experiments.pytorch_Model import ModifiedXception
 from experiments.Model_All_Step import All_Step
+from Training_Tools.PreProcess import Training_Precesses
 from torchinfo import summary
 import pandas as pd
 import numpy as np
@@ -13,7 +14,7 @@ import torch.nn as nn
 import time
 
 class experiments():
-    def __init__(self, Image_Size, Model_Name, Experiment_Name, Generator_Batch_Size, Epoch, Train_Batch_Size, tools, Number_Of_Classes, status):
+    def __init__(self, Image_Size, Model_Name, Experiment_Name, Epoch, Train_Batch_Size, tools, Number_Of_Classes, status):
         '''   
             # 實驗物件
 
@@ -49,7 +50,6 @@ class experiments():
 
         self.model_name = Model_Name # 取名，告訴我我是用哪個模型(可能是預處理模型/自己設計的模型)
         self.experiment_name = Experiment_Name
-        self.generator_batch_size = Generator_Batch_Size
         self.epoch = Epoch
         self.train_batch_size = Train_Batch_Size
         self.layers = 1
@@ -62,7 +62,7 @@ class experiments():
 
         pass
 
-    def processing_main(self, Training_Dataset, counter):
+    def processing_main(self, Training_Data, Training_Label, counter):
         Train, Test, Validation = self.Topic_Tool.Get_Save_Roots(self.Status) # 要換不同資料集就要改
 
         start = time.time()
@@ -72,22 +72,15 @@ class experiments():
 
         # 將處理好的test Data 與 Validation Data 丟給這個物件的變數
         self.test, self.test_label = self.cut_image.test, self.cut_image.test_label
-        self.validation, self.validation_label = self.cut_image.validation, self.cut_image.validation_label
 
-        Testing_Dataset = self.Topic_Tool.Convert_Data_To_DataSet_And_Put_To_Dataloader(self.test, self.test_label, 1)
-        Validation_Dataset = self.Topic_Tool.Convert_Data_To_DataSet_And_Put_To_Dataloader(self.validation, self.validation_label, 1)
+        PreProcess = Training_Precesses(Training_Data, Training_Label, self.test, self.test_label)
 
         cnn_model = self.construct_model() # 呼叫讀取模型的function
         print(summary(cnn_model, input_size=(int(self.train_batch_size / 2), 3, self.Image_Size, self.Image_Size)))
         for name, parameters in cnn_model.named_parameters():
             print(f"Layer Name: {name}, Parameters: {parameters.size()}")
 
-        step = All_Step(Training_Dataset, Testing_Dataset, Validation_Dataset, cnn_model, self.epoch, self.Number_Of_Classes, self.model_name)
-            
-            # model_dir = '../save_the_best_model/Topic/Remove background with Normal image/best_model( 2023-10-17 )-2.h5' # 這是一個儲存模型權重的路徑，每一個模型都有一個自己權重儲存的檔
-            # if os.path.exists(model_dir): # 如果這個檔案存在
-            #     cnn_model.load_weights(model_dir) # 將模型權重讀出來
-            #     print("讀出權重\n") 
+        step = All_Step(PreProcess, self.train_batch_size, cnn_model, self.epoch, self.Number_Of_Classes, self.model_name)
         print("\n\n\n讀取訓練資料(70000)執行時間：%f 秒\n\n" % (end - start))
 
         train_losses, val_losses, train_accuracies, val_accuracies, Epoch = step.Training_Step(self.model_name, counter)

experiments/pytorch_Model.py

@@ -10,41 +10,33 @@ class ModifiedXception(nn.Module):
     def __init__(self, num_classes):
         super(ModifiedXception, self).__init__()
         
-        # 加載 Xception 預訓練模型，去掉最後一層 (fc 層)
+        # Load Xception pre-trained model (full model, not just features)
         self.base_model = timm.create_model(
-            'xception', 
-            pretrained=True, 
-            features_only=True, # 只保留特徵提取部分
-            out_indices=[3] # 選擇特徵層索引（根據模型結構）
-            )
+            'xception',
+            pretrained=True,
+            drop_rate=0.0,  # Optional: adjust dropout if needed
+        )
         
-        # 自定義分類頭
+        # Replace the default global pooling with AdaptiveAvgPool2d
+        self.base_model.global_pool = nn.AdaptiveAvgPool2d(output_size=1)  # Output size of 1x1 spatially
+        
+        # Replace the final fully connected layer with Identity to get features
+        self.base_model.fc = nn.Identity()  # Output will be 2048 (Xception's default feature size)
+        
+        # Custom head: Linear from 2048 to 1370, additional 1370 layer, then to num_classes
         self.custom_head = nn.Sequential(
-            nn.AdaptiveAvgPool2d(1),  # Global Average Pooling,
-            nn.Flatten(),
-            nn.Linear(728, 368),    # Xception 輸出特徵維度為2048
-            nn.ReLU(),               # 可選激活函數
-            nn.Linear(368, num_classes),
-            nn.Sigmoid()
+            nn.Linear(2048, 1025),  # From Xception’s 2048 features to 1370
+            nn.ReLU(),              # Activation
+            nn.Dropout(0.6),        # Dropout for regularization
+            nn.Linear(1025, num_classes),  # Final output layer
+            nn.Sigmoid()            # Sigmoid for binary/multi-label classification
         )
 
-        # self.base_model.fc = nn.Identity()  # 移除原來的 fully connected 層
-        
-        # # 新增全局平均池化層、隱藏層和輸出層
-        # self.global_avg_pool = nn.AdaptiveAvgPool2d(1)  # 全局平均池化
-        # self.hidden_layer = nn.Linear(2048, 1370)  # 隱藏層，輸入大小取決於 Xception 的輸出大小
-        # self.output_layer = nn.Linear(1370, 2)  # 輸出層，依據分類數目設定
-        
-        # # 激活函數與 dropout
-        # self.relu = nn.ReLU()
-        # self.dropout = nn.Dropout(0.6)
-
     def forward(self, x):
-        x = self.base_model(x)               # Xception 主體
-        x = x[0]
-        output = self.custom_head(x)
-        # x = self.global_avg_pool(x)           # 全局平均池化
-        # x = self.relu(self.hidden_layer(x))   # 隱藏層 + ReLU
-        # x = self.dropout(x)                   # Dropout
-        # x = self.output_layer(x)              # 輸出層
+        # Pass through the base Xception model (up to global pooling)
+        x = self.base_model.forward_features(x)  # Get feature maps
+        x = self.base_model.global_pool(x)       # Apply AdaptiveAvgPool2d (output: [B, 2048, 1, 1])
+        x = x.flatten(1)                         # Flatten to [B, 2048]
+        x = self.base_model.fc(x)                # Identity layer (still [B, 2048])
+        output = self.custom_head(x)             # Custom head processing
         return output

experiments/topic_model.py

@@ -1,298 +0,0 @@
-from convolution_model_tools.convolution_2D_tools import model_2D_tool
-from dense_model_tools.dense_tools import model_Dense_Layer
-from all_models_tools.all_model_tools import add_optimizers_function, add_Activative, add_dropout, call_back
-from keras.activations import softmax, sigmoid
-from keras.applications import VGG19, ResNet50, NASNetLarge, DenseNet201, Xception
-from keras.applications.efficientnet_v2 import EfficientNetV2L
-from keras.layers import BatchNormalization, Flatten, GlobalAveragePooling2D, MaxPooling2D, Dense, Conv2D, Dropout, TimeDistributed, LSTM, Input
-from keras import regularizers
-
-def one_layer_cnn_model():
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    img_Input = tools.add_2D_input()
-    x = tools.add_Convolution2D(img_Input, 32)
-    x = add_Activative(x)
-    x = tools.add_MaxPooling(x)
-
-    x = tools.add_Convolution2D(x, 64)
-    x = add_Activative(x)
-    x = tools.add_MaxPooling(x)
-
-    flatter = tools.add_flatten(x)
-
-    dense = dense_tool.add_dense(64, flatter)
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(32, dense)
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-    return img_Input, dense
-
-def find_example_cnn_model():
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    img_Input = tools.add_2D_input()
-
-    x = tools.add_Convolution2D(img_Input, 16)
-    x = add_Activative(x)
-    x = add_dropout(x, 0.25)
-
-    x = tools.add_Convolution2D(x, 32)
-    x = add_Activative(x)
-    x = add_dropout(x, 0.25)
-
-    x = tools.add_MaxPooling(x)
-
-    x = tools.add_Convolution2D(x, 64)
-    x = add_Activative(x)
-    x = add_dropout(x, 0.25)
-
-    x = tools.add_MaxPooling(x)
-
-    x = tools.add_Convolution2D(x, 128)
-    x = add_Activative(x)
-    x = add_dropout(x, 0.25)
-
-    x = tools.add_MaxPooling(x)
-
-    flatter = tools.add_flatten(x)
-
-    dense = dense_tool.add_dense(64, flatter)
-    dense = add_Activative(dense)
-    dense = add_dropout(dense, 0.25)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, sigmoid)
-
-    return img_Input, dense
-
-def change_example_cnn_model():
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    img_Input = tools.add_2D_input()
-
-    x = tools.add_Convolution2D(img_Input, 16)
-    x = add_Activative(x)
-    x = tools.add_batchnomlization(x)
-
-    x = tools.add_Convolution2D(x, 32)
-    x = add_Activative(x)
-    x = tools.add_batchnomlization(x)
-
-    x = tools.add_MaxPooling(x)
-
-    x = tools.add_Convolution2D(x, 64)
-    x = add_Activative(x)
-    x = tools.add_batchnomlization(x)
-
-    x = tools.add_MaxPooling(x)
-
-    x = tools.add_Convolution2D(x, 128)
-    x = add_Activative(x)
-    x = tools.add_batchnomlization(x)
-
-    x = tools.add_MaxPooling(x)
-
-    flatter = tools.add_flatten(x)
-
-    dense = dense_tool.add_dense(64, flatter)
-    dense = add_Activative(dense)
-    dense = add_dropout(dense, 0.3)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return img_Input, dense
-
-def two_convolution_cnn_model():
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    img_Input = tools.add_2D_input()
-    x = tools.add_two_floors_convolution2D(img_Input, 32)
-    x = tools.add_MaxPooling(x)
-
-    x = tools.add_two_floors_convolution2D(x, 64)
-    x = tools.add_MaxPooling(x)
-
-    flatter = tools.add_flatten(x)
-
-    dense = dense_tool.add_dense(64, flatter)
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(32, dense)
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-    return img_Input, dense  
-
-def VGG19_model():
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    vgg19 = VGG19(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(vgg19.output)
-    dense = dense_tool.add_dense(64, flatten)
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return vgg19, dense  
-
-def Resnet50_model():
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    vgg19 = ResNet50(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(vgg19.output)
-    dense = dense_tool.add_dense(64, flatten)
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return vgg19, dense  
-
-def DenseNet201_model():
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    Densenet201 = DenseNet201(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(Densenet201.output)
-    dense = dense_tool.add_dense(64, flatten)
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return Densenet201, dense
-
-def Xception_model():
-    xception = Xception(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = Flatten()(xception.output)
-    dense = Dense(units = 64, activation = "relu")(flatten)
-    dense = Dense(units = 7, activation = "softmax")(dense)
-
-    return xception, dense
-
-def cnn_LSTM():
-    head = Input(shape = (150, 150, 3))
-    inputs = Conv2D(filters = 64, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(head)
-    inputs = Conv2D(filters = 64, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = MaxPooling2D(strides = 2, pool_size = (2, 2))(inputs)
-    inputs = Dropout(0.25)(inputs)
-
-    inputs = Conv2D(filters = 128, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = Conv2D(filters = 128, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = MaxPooling2D(strides = 2, pool_size = (2, 2))(inputs)
-    inputs = Dropout(0.25)(inputs)
-
-    inputs = Conv2D(filters = 256, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = Conv2D(filters = 256, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = MaxPooling2D(strides = 2, pool_size = (2, 2))(inputs)
-    inputs = Dropout(0.25)(inputs)
-
-    inputs = Conv2D(filters = 512, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = Conv2D(filters = 512, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = Conv2D(filters = 512, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = MaxPooling2D(strides = 2, pool_size = (2, 2))(inputs)
-    inputs = Dropout(0.25)(inputs)
-
-    inputs = Conv2D(filters = 512, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = Conv2D(filters = 512, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = Conv2D(filters = 512, strides = 1, kernel_size = (3, 3), padding = "same", activation = "relu")(inputs)
-    inputs = MaxPooling2D(strides = 2, pool_size = (2, 2))(inputs)
-    inputs = Dropout(0.25)(inputs)
-    inputs = TimeDistributed(Flatten())(inputs)
-
-    inputs = LSTM(units = 49)(inputs)
-    inputs = Dense(units = 64)(inputs)
-    output = Dense(units = 7, activation = "softmax")(inputs)
-
-    return head, output
-
-def add_regularizers_L1(): # 比較正規化
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    Resnet50 = ResNet50(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(Resnet50.output)
-    dense = dense_tool.add_regularizer_dense(64, flatten, regularizers.L1())
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return Resnet50, dense
-
-def add_regularizers_L2(): # 比較正規化
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    Resnet50 = ResNet50(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(Resnet50.output)
-    dense = dense_tool.add_regularizer_dense(64, flatten, regularizers.L2())
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return Resnet50, dense
-
-def add_regularizers_L1L2(): # 比較正規化
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    Resnet50 = ResNet50(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(Resnet50.output)
-    dense = dense_tool.add_regularizer_dense(64, flatten, regularizers.L1L2())
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return Resnet50, dense
-
-def add_layers1_L2(Dense_layers): # 比較正規化
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-    layers = 32
-
-    Densenet201 = DenseNet201(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(Densenet201.output)
-
-    for layer in range(Dense_layers):
-        dense = dense_tool.add_regularizer_kernel_dense(unit = layers, input_data = flatten, regularizer = regularizers.L2())
-        dense = add_Activative(dense)
-        layers *= 2
-
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return Densenet201, dense
-
-def add_layers_another_L2(Dense_layers, layers): # 比較正規化
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    Densenet201 = DenseNet201(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(Densenet201.output)
-
-    for layer in range(Dense_layers):
-        dense = dense_tool.add_regularizer_dense(unit = layers, input_data = flatten, regularizer = regularizers.L2())
-        dense = add_Activative(dense)
-        layers /= 2
-
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return Densenet201, dense
-
-def add_bias_regularizers(): # 比較正規化
-    tools = model_2D_tool()
-    dense_tool = model_Dense_Layer()
-
-    Resnet50 = ResNet50(include_top = False, weights = "imagenet", input_shape = (120, 120, 3))
-    flatten = tools.add_flatten(Resnet50.output)
-    dense = dense_tool.add_regularizer_bias_dense(64, flatten, regularizers.L2())
-    dense = add_Activative(dense)
-    dense = dense_tool.add_dense(7, dense)
-    dense = add_Activative(dense, softmax)
-
-    return Resnet50, dense

main.py

@@ -8,7 +8,6 @@ from Calculate_Process.Calculate import Calculate
 from merge_class.merge import merge
 import time
 import torch
-import os
 
 if __name__ == "__main__":
     # 測試GPU是否可用
@@ -23,7 +22,7 @@ if __name__ == "__main__":
     tool.Set_Labels()
     tool.Set_Save_Roots()
 
-    Status = 2 # 決定要使用什麼資料集
+    Status = 1 # 決定要使用什麼資料集
     Labels = tool.Get_Data_Label()
     Trainig_Root, Testing_Root, Validation_Root = tool.Get_Save_Roots(Status) # 一般的
     Generator_Root = tool.Get_Generator_Save_Roots(Status)
@@ -37,14 +36,13 @@ if __name__ == "__main__":
 
     Model_Name = "Xception" # 取名，告訴我我是用哪個模型(可能是預處理模型/自己設計的模型)
     Experiment_Name = "Xception Skin to train Normal stomach cancer"
-    Generator_Batch_Size = 50
     Epoch = 10000
-    Train_Batch_Size = 50
+    Train_Batch_Size = 64
     Image_Size = 256
 
     Prepare = Load_Data_Prepare()
     loading_data = Load_ImageGenerator(Trainig_Root, Testing_Root, Validation_Root, Generator_Root, Labels, Image_Size)
-    experiment = experiments(Image_Size, Model_Name, Experiment_Name, Generator_Batch_Size, Epoch, Train_Batch_Size, tool, Classification, Status)
+    experiment = experiments(Image_Size, Model_Name, Experiment_Name, Epoch, Train_Batch_Size, tool, Classification, Status)
     image_processing = Read_image_and_Process_image(Image_Size)
     Merge = merge()
     Calculate_Tool = Calculate()
@@ -81,17 +79,7 @@ if __name__ == "__main__":
 
         start = time.time()
         trains_Data_Image = image_processing.Data_Augmentation_Image(training_data) # 讀檔
-
-        # total_trains, train_label = shuffle_data(trains_Data_Image, training_label) # 將資料打亂
-        # training_data = list(total_trains) # 轉換資料型態
-
-        training_data, train_label = image_processing.image_data_processing(trains_Data_Image, training_label) # 將讀出來的檔做正規化。降label轉成numpy array 格式
-        Training_Dataset = tool.Convert_Data_To_DataSet_And_Put_To_Dataloader(training_data, train_label, Train_Batch_Size)
-
-        # 查看Dataloader的Shape
-        for idx, data in enumerate(Training_Dataset):
-            datas = data[0]
-            print(f"Shape: {datas.shape}")
+        Training_Data, Training_Label = image_processing.image_data_processing(trains_Data_Image, training_label) # 將讀出來的檔做正規化。降label轉成numpy array 格式
 
 
         # training_data = image_processing.normalization(training_data)
@@ -100,7 +88,7 @@ if __name__ == "__main__":
         end = time.time()
         print("\n\n\n讀取訓練資料(70000)執行時間：%f 秒\n\n" % (end - start))          
         
-        loss, accuracy, precision, recall, AUC, f = experiment.processing_main(Training_Dataset, Run_Range) # 執行訓練方法
+        loss, accuracy, precision, recall, AUC, f = experiment.processing_main(Training_Data, Training_Label, Run_Range) # 執行訓練方法
         Calculate_Tool.Append_numbers(loss, accuracy, precision, recall, AUC, f)
 
     print("實驗結果")

test.ipynb

@@ -1857,6 +1857,36 @@
     "model.base_model.body.conv4.pointwise"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[(array([0, 3, 4, 5, 6, 7]), array([1, 2])), (array([0, 1, 2, 4, 6, 7]), array([3, 5])), (array([1, 2, 3, 5, 6, 7]), array([0, 4])), (array([0, 1, 2, 3, 4, 5, 6]), array([7])), (array([0, 1, 2, 3, 4, 5, 7]), array([6]))]\n",
+      "[0 1 2 3 4 7] [5 6]\n",
+      "[0 1 2 5 6 7] [3 4]\n",
+      "[1 2 3 4 5 6] [0 7]\n",
+      "[0 2 3 4 5 6 7] [1]\n",
+      "[0 1 3 4 5 6 7] [2]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import KFold\n",
+    "\n",
+    "k = KFold(n_splits = 5, shuffle = True)\n",
+    "a = [1, 2, 3, 4 ,5, 6,7, 8]\n",
+    "\n",
+    "print(list(k.split(a)))\n",
+    "\n",
+    "for d, b in k.split(a):\n",
+    "    print(d, b)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1881,7 +1911,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.10"
+   "version": "3.11.11"
   }
  },
  "nbformat": 4,