from all_models_tools.all_model_tools import call_back from Read_and_process_image.ReadAndProcess import Read_image_and_Process_image from draw_tools.draw import plot_history, Confusion_Matrix_of_Two_Classification 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 draw_tools.Grad_cam import Grad_CAM from sklearn.metrics import confusion_matrix from experiments.pytorch_Model import ModifiedXception from Image_Process.Image_Generator import Image_generator from Model_All_Step import All_Step import pandas as pd import numpy as np import torch import torch.nn as nn import time class experiments(): def __init__(self, tools, Number_Of_Classes, status): ''' # 實驗物件 ## 說明: * 用於開始訓練pytorch的物件，裡面分為數個方法，負責處理實驗過程的種種 ## parmeter: * Topic_Tool: 讀取訓練、驗證、測試的資料集與Label等等的內容 * cut_image: 呼叫切割影像物件 * merge: 合併的物件 * model_name: 模型名稱，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: 實驗名稱 * epoch: 訓練次數 * train_batch_size: 訓練資料的batch * convolution_name: Grad-CAM的最後一層的名稱 * Number_Of_Classes: Label的類別 * Status: 選擇現在資料集的狀態 * device: 決定使用GPU或CPU ## Method: * processing_main: 實驗物件的進入點 * construct_model: 決定實驗用的Model * Training_Step: 訓練步驟，開始進行訓練驗證的部分 * Evaluate_Model: 驗證模型的準確度 * record_matrix_image: 劃出混淆矩陣(熱力圖) * record_everyTime_test_result: 記錄我單次的訓練結果並將它輸出到檔案中 ''' self.Topic_Tool = tools 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.image_processing = Read_image_and_Process_image() self.merge = merge() self.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) self.experiment_name = "Xception Skin to train Normal stomach cancer" # self.file_name = "Remove background of Chickenpox with normal image" self.generator_batch_size = 50 self.epoch = 10000 self.train_batch_size = 128 self.layers = 1 self.convolution_name = "block14_sepconv2" self.Number_Of_Classes = Number_Of_Classes self.Grad = "" self.Status = status self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') pass def processing_main(self, train, train_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() self.cut_image.process_main(Test, Validation) # 呼叫處理test Data與Validation Data的function end = time.time() print("讀取testing與validation資料(154)執行時間：%f 秒\n" % (end - start)) # Generator = Image_generator("", "") # 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 self.Topic_Tool.Set_Zips(train, train_label, "Training") self.Topic_Tool.Set_Zips(self.test, self.test_label, "Testing") self.Topic_Tool.Set_Zips(self.validation, self.validation_label, "Validation") self.Training_Zip, self.Testing_Zip, self.Validation_Zip = self.Topic_Tool.Get_Zip() # self.Grad = Grad_CAM(self.Topic_Tool.Get_Data_Label(), self.test_label, self.experiment_name, self.convolution_name) cnn_model = self.construct_model() # 呼叫讀取模型的function step = All_Step(self.Training_Zip, self.Testing_Zip, self.Validation_Zip, cnn_model, self.epoch, self.Number_Of_Classes) # 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") 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 = step.Training_Step(self.model_name, counter) loss, accuracy, precision, recall, AUC, f1, True_Label, Predict_Label = step.Evaluate_Model(cnn_model) self.record_matrix_image(True_Label, Predict_Label, self.model_name, counter) print(self.record_everyTime_test_result(loss, accuracy, precision, recall, AUC, f1, counter, self.experiment_name)) # 紀錄當前訓練完之後的預測結果，並輸出成csv檔 Losses = [train_losses, val_losses] Accuracyes = [train_accuracies, val_accuracies] plot_history(self.epoch, Losses, Accuracyes, "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, self.test) return loss, accuracy, precision, recall, AUC, f1 def construct_model(self): '''決定我這次訓練要用哪個model''' cnn_model = ModifiedXception() if torch.cuda.device_count() > 1: cnn_model = nn.DataParallel(cnn_model) cnn_model = cnn_model.to(self.device) return cnn_model def record_matrix_image(self, True_Labels, Predict_Labels, model_name, index): '''劃出混淆矩陣(熱力圖)''' # 計算混淆矩陣 matrix = confusion_matrix(True_Labels, Predict_Labels) Confusion_Matrix_of_Two_Classification(model_name, matrix, index) # 呼叫畫出confusion matrix的function return matrix.real def record_everyTime_test_result(self, loss, accuracy, precision, recall, auc, f, indexs, model_name, Matrix): '''記錄我單次的訓練結果並將它輸出到檔案中''' File = Process_File() Dataframe = pd.DataFrame( { "model_name" : str(model_name), "loss" : "{:.2f}".format(loss), "precision" : "{:.2f}%".format(precision * 100), "recall" : "{:.2f}%".format(recall * 100), "accuracy" : "{:.2f}%".format(accuracy * 100), "f" : "{:.2f}%".format(f * 100), "AUC" : "{:.2f}%".format(auc * 100) }, index = [indexs]) File.Save_CSV_File("train_result", Dataframe) # File.Save_TXT_File("Matrix_Result : " + str(Matrix), model_name + "_train" + str(indexs)) return Dataframe