如何保存经过训练的FCN模型并在经过训练的FCN模型上测试新图像?

本文介绍了如何保存经过训练的FCN模型并在经过训练的FCN模型上测试新图像?的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 问题描述

我正在使用此代码来训练FCN，我已成功运行了此代码.但是，我想在这种训练有素的模型上测试新图像，有人可以帮助我吗?

I am using this code to train FCN, I have succssfully run this code. However, I want to test new images on this trained model, can anyone help me?

#Training from keras import optimizers sgd = optimizers.SGD(lr=1E-2, decay=5**(-4), momentum=0.9, nesterov=True) modelpile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) hist1 = model.fit(X_train,y_train, validation_data=(X_test,y_test), batch_size=2,epochs=20,verbose=1) for key in ['loss', 'acc', 'val_loss', 'val_acc']: plt.plot(hist1.history[key],label=key) plt.legend() plt.show() y_pred = model.predict(X_test) y_predi = np.argmax(y_pred, axis=3) y_testi = np.argmax(y_test, axis=3) print(y_testi.shape,y_predi.shape)

推荐答案

如keras常见问题解答( keras.io/getting-started/faq/#how-can-i-save-a-keras-model ):

As stated in the keras FAQs (keras.io/getting-started/faq/#how-can-i-save-a-keras-model):

要将模型保存到磁盘，您可以执行以下操作:

To save your model to your disk you can do:

model.save("my_model_file.h5")

并在以后再次加载它或在另一个文件中加载它以供使用:

And to load it again later or in another file for using it:

from keras.models import load_model model = load_model("my_model_file.h5") y_pred = model.predict(X_test)