tensorflow2.0——history保存loss和acc


history包含以下幾個屬性:
訓練集loss: loss
測試集loss: val_loss
訓練集准確率: sparse_categorical_accuracy
測試集准確率: val_sparse_categorical_accuracy

my_model.compile(optimizer=opt,loss=tf.keras.losses.MSE)
history=my_model.fit(train_high0_img,train_rain,validation_data=(test_high0_img,test_rain),epochs=epochs, validation_freq=1,batch_size=bat)
#   history包含以下幾個屬性:
# 訓練集loss: loss
# 測試集loss: val_loss
# 訓練集准確率: sparse_categorical_accuracy
# 測試集准確率: val_sparse_categorical_accuracy
# acc = history.history['sparse_categorical_accuracy']
# val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
# print('acc:',acc)
# print('val_acc:',val_acc)
print('loss:',loss)
print('val_loss:',val_loss)

 


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM