直接上程式碼:
fig_loss = np.zeros([n_epoch]) fig_acc1 = np.zeros([n_epoch]) fig_acc2= np.zeros([n_epoch]) for epoch in range(n_epoch): start_time = time.time() #training train_loss, train_acc, n_batch = 0, 0, 0 for x_train_a, y_train_a in minibatches(x_train, y_train, batch_size, shuffle=True): _,err,ac=sess.run([train_op,loss,acc], feed_dict={x: x_train_a, y_: y_train_a}) train_loss += err; train_acc += ac; n_batch += 1 summary_str = sess.run(merged_summary_op,feed_dict={x: x_train_a, y_: y_train_a}) summary_writer.add_summary(summary_str, epoch) print(" train loss: %f" % (np.sum(train_loss)/ n_batch)) print(" train acc: %f" % (np.sum(train_acc)/ n_batch)) fig_loss[epoch] = np.sum(train_loss)/ n_batch fig_acc1[epoch] = np.sum(train_acc) / n_batch #validation val_loss, val_acc, n_batch = 0, 0, 0 for x_val_a, y_val_a in minibatches(x_val, y_val, batch_size, shuffle=False): err, ac = sess.run([loss,acc], feed_dict={x: x_val_a, y_: y_val_a}) val_loss += err; val_acc += ac; n_batch += 1 print(" validation loss: %f" % (np.sum(val_loss)/ n_batch)) print(" validation acc: %f" % (np.sum(val_acc)/ n_batch)) fig_acc2[epoch] = np.sum(val_acc) / n_batch # 訓練loss圖 fig, ax1 = plt.subplots() lns1 = ax1.plot(np.arange(n_epoch), fig_loss, label="Loss") ax1.set_xlabel('iteration') ax1.set_ylabel('training loss') # 訓練和驗證兩種準確率曲線圖放在一張圖中 fig2, ax2 = plt.subplots() ax3 = ax2.twinx()#由ax2圖生成ax3圖 lns2 = ax2.plot(np.arange(n_epoch), fig_acc1, label="Loss") lns3 = ax3.plot(np.arange(n_epoch), fig_acc2, label="Loss") ax2.set_xlabel('iteration') ax2.set_ylabel('training acc') ax3.set_ylabel('val acc') # 合併圖例 lns = lns3 + lns2 labels = ["train acc", "val acc"] plt.legend(lns, labels, loc=7) plt.show()
結果:
補充知識:tensorflow2.x實時繪製訓練時的損失和準確率
我就廢話不多說了,大家還是直接看程式碼吧!
sgd = SGD(lr=float(model_value[3]), decay=1e-6, momentum=0.9, nesterov=True) model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) # validation_split:0~1之間的浮點數,用來指定訓練集的一定比例資料作為驗證集 history=model.fit(self.x_train, self.y_train, batch_size=self.batch_size, epochs=self.epoch_size, class_weight = 'auto', validation_split=0.1) # 繪製訓練 & 驗證的準確率值 plt.plot(history.history['accuracy']) plt.plot(history.history['val_accuracy']) plt.title('Model accuracy') plt.ylabel('Accuracy') plt.xlabel('Epoch') plt.legend(['Train', 'Test'], loc='upper left') plt.show() # 繪製訓練 & 驗證的損失值 plt.plot(history.history['loss']) plt.plot(history.history['val_loss']) plt.title('Model loss') plt.ylabel('Loss') plt.xlabel('Epoch') plt.legend(['Train', 'Test'], loc='upper left') plt.show() print("savemodel---------------") model.save(os.path.join(model_value[0],'model3_3.h5')) #輸出損失和精確度 score = model.evaluate(self.x_test, self.y_test, batch_size=self.batch_size)
[hongdian2012 ] 在tensorflow下利用plt畫論文中loss,acc等曲線圖例項已經有290次圍觀