20250224 commits: Data Argumentation had done 5x, and validation Accuracy just only have 33%

Image_Process/Image_Generator.py

@@ -7,6 +7,7 @@ from Training_Tools.Tools import Tool
 import numpy as np
 from PIL import Image
 import torch
+import cv2
 
 class Image_generator():
     '''製作資料強化'''
@@ -26,36 +27,37 @@ class Image_generator():
             這裡我想要做的是依照paper上的資料強化IMAGE DATA COLLECTION AND IMPLEMENTATION OF DEEP LEARNING-BASED MODEL IN DETECTING MONKEYPOX DISEASE USING MODIFIED VGG16
             產生出資料強化後的影像
         '''
-        print("\nAugmentation one Generator image")
+        for i in range(1, 5, 1):
-        data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, 1, data_size)
+            print("\nAugmentation one Generator image")
-        self.stop += data_size
+            data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, i, data_size)
+            self.stop += data_size
 
-        # 製作標準資料增強
+        # # 製作標準資料增強
-        '''
+        # '''
-            這裡我想要做的是依照paper上的資料強化IMAGE DATA COLLECTION AND IMPLEMENTATION OF DEEP LEARNING-BASED MODEL IN DETECTING MONKEYPOX DISEASE USING MODIFIED VGG16
+        #     這裡我想要做的是依照paper上的資料強化IMAGE DATA COLLECTION AND IMPLEMENTATION OF DEEP LEARNING-BASED MODEL IN DETECTING MONKEYPOX DISEASE USING MODIFIED VGG16
-            產生出資料強化後的影像
+        #     產生出資料強化後的影像
-        '''
+        # '''
-        print("\nAugmentation two Generator image")
+        # print("\nAugmentation two Generator image")
-        data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, 2, data_size)
+        # data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, 2, data_size)
-        self.stop += data_size
+        # self.stop += data_size
 
-        # 製作標準資料增強
+        # # 製作標準資料增強
-        '''
+        # '''
-            這裡我想要做的是依照paper上的資料強化IMAGE DATA COLLECTION AND IMPLEMENTATION OF DEEP LEARNING-BASED MODEL IN DETECTING MONKEYPOX DISEASE USING MODIFIED VGG16
+        #     這裡我想要做的是依照paper上的資料強化IMAGE DATA COLLECTION AND IMPLEMENTATION OF DEEP LEARNING-BASED MODEL IN DETECTING MONKEYPOX DISEASE USING MODIFIED VGG16
-            產生出資料強化後的影像
+        #     產生出資料強化後的影像
-        '''
+        # '''
-        print("\nAugmentation three Generator image")
+        # print("\nAugmentation three Generator image")
-        data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, 3, data_size)
+        # data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, 3, data_size)
-        self.stop += data_size
+        # self.stop += data_size
         
 
-        # 製作標準資料增強
+        # # 製作標準資料增強
-        '''
+        # '''
-            這裡我想要做的是依照paper上的資料強化IMAGE DATA COLLECTION AND IMPLEMENTATION OF DEEP LEARNING-BASED MODEL IN DETECTING MONKEYPOX DISEASE USING MODIFIED VGG16
+        #     這裡我想要做的是依照paper上的資料強化IMAGE DATA COLLECTION AND IMPLEMENTATION OF DEEP LEARNING-BASED MODEL IN DETECTING MONKEYPOX DISEASE USING MODIFIED VGG16
-            產生出資料強化後的影像
+        #     產生出資料強化後的影像
-        '''
+        # '''
-        print("\nAugmentation four Generator image")
+        # print("\nAugmentation four Generator image")
-        data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, 4, data_size)
+        # data_size = self.get_processing_Augmentation(Training_Dict_Data_Root, 4, data_size)
 
         print()
 
@@ -97,7 +99,12 @@ class Image_generator():
 
                     img = img.permute(2, 0, 1)
                     img = Transform(img)
-                    img_pil = transforms.ToPILImage()(img)
+
+                    # 轉換為 NumPy 陣列並從 BGR 轉為 RGB
+                    img_np = img.numpy().transpose(1, 2, 0)  # 轉回 HWC 格式
+                    img_np = cv2.cvtColor(img_np, cv2.COLOR_BGR2RGB)  # BGR 轉 RGB
+
+                    img_pil = transforms.ToPILImage()(img_np)
                     File.Save_PIL_File("image_" + label + str(data_size) + ".png", save_root, img_pil) # 存檔
                     data_size += 1
 
@@ -109,7 +116,7 @@ class Image_generator():
         img = image_processing.Data_Augmentation_Image(self.get_data_roots[label])
         img = torch.tensor(img)
 
-        self.stop = len(img) * 1.5
+        self.stop = len(img) * 5
         return img
     
     def Generator_Content(self, judge): # 影像資料增強

Load_process/Load_Indepentend.py

@@ -45,8 +45,8 @@ class Load_Indepentend_Data():
             Classify_Label.append(test_label)
             i += 1
 
-        original_test_root = self.merge.merge_data_main(classify_image, 0, 2)
+        original_test_root = self.merge.merge_data_main(classify_image, 0)
-        original_test_label = self.merge.merge_data_main(Classify_Label, 0, 2)
+        original_test_label = self.merge.merge_data_main(Classify_Label, 0)
 
         test = []
         test = image_processing.Data_Augmentation_Image(original_test_root)

experiments/experiment.py

@@ -3,7 +3,6 @@ from draw_tools.Grad_cam import Grad_CAM
 from Load_process.Load_Indepentend import Load_Indepentend_Data
 from _validation.ValidationTheEnterData import validation_the_enter_data
 from Load_process.file_processing import Process_File
-from merge_class.merge import merge
 from sklearn.metrics import confusion_matrix
 from experiments.pytorch_Model import ModifiedXception
 from experiments.Model_All_Step import All_Step
@@ -48,7 +47,6 @@ class experiments():
 
         self.validation_obj = validation_the_enter_data() # 呼叫驗證物件
         self.cut_image = Load_Indepentend_Data(self.Topic_Tool.Get_Data_Label(), self.Topic_Tool.Get_OneHot_Encording_Label()) # 呼叫切割影像物件
-        self.merge = merge()
 
         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
@@ -105,7 +103,7 @@ class experiments():
         Losses = [train_losses, val_losses]
         Accuracies = [train_accuracies, val_accuracies]
         plot_history(Epoch + 1, Losses, Accuracies, "train" + str(counter), self.experiment_name) # 將訓練結果化成圖，並將化出來的圖丟出去儲存
-        self.Grad.process_main(cnn_model, counter, Testing_Dataset)
+        # self.Grad.process_main(cnn_model, counter, Testing_Dataset)
 
         return loss, accuracy, precision, recall, AUC, f1
 

main.py

@@ -31,6 +31,7 @@ if __name__ == "__main__":
     # 取得One-hot encording 的資料
     tool.Set_OneHotEncording(Labels)
     Encording_Label = tool.Get_OneHot_Encording_Label()
+    
     Label_Length = len(Labels)
     Classification = 3 # 分類數量
 

merge_class/merge.py

@@ -18,10 +18,10 @@ class merge:
     def get_judge_status(self):
         return self.__judge
     
-    def merge_all_image_data(self, Classify1, Classify2):
+    def merge_all_image_data(self, Classify1, Classify2, Number_Of_Classes = 2):
         merged_data = [Classify1, Classify2]
 
-        return self.merge_data_main(merged_data, 0, 2)
+        return self.merge_data_main(merged_data, 0, Number_Of_Classes)
 
     def merge_data_main(self, merge_data, merge_start_index, total_merge_number = 3):
         '''
@@ -31,6 +31,7 @@ class merge:
             * merge_start_index: 合併資料的起始位置
             * total_merge_numbers: 總共要合併的數量
         '''
+
         if self.validation.validation_type(merge_data, dict):
             self.set_merge_data(merge_data)
             return self.merge_dict_to_list_data(merge_start_index, total_merge_number)
@@ -50,12 +51,12 @@ class merge:
     
     def merge_dict_to_dict(self, original : dict, myself):
         keys = list(original.keys())
-        data = {
+        data = {}
-            keys[0]: [],
-            keys[1]: [],
-        }
         
         for key in keys:
+            Content = {key : []}
+            data.update(Content)
+
             tempData = [original[key], myself[key]]
             end = 2