Tensorflow 保持卷积神经网络模型

如何保留卷积神经网络的训练结果，以便不同的数据可以再次用于测试？

如果您使用tensorflow的keras，则可以将模型保存为json格式，并将权重保存为hdf5文件格式

# keras library import  for Saving and loading model and weights

from keras.models import model_from_json
from keras.models import load_model

# serialize model to JSON
#  the keras model which is trained is defined as 'model' in this example
model_json = model.to_json()


with open("model_num.json", "w") as json_file:
    json_file.write(model_json)

# serialize weights to HDF5
model.save_weights("model_num.h5")

创建了包含模型和权重的文件“model_num.h5”和“model_num.json”

要使用相同的训练模型进行进一步测试，只需加载hdf5文件并将其用于不同数据的预测。 下面介绍如何从保存的文件加载模型

# load json and create model
json_file = open('model_num.json', 'r')

loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)

# load weights into new model
loaded_model.load_weights("model_num.h5")
print("Loaded model from disk")

model.save('model_num.hdf5')
loaded_model=load_model('model_num.hdf5')

要预测不同的数据，可以使用

loaded_model.predict_classes("your_test_data here")

---

如果将keras与tensorflow一起使用，则可以将模型保存为json格式，并将权重保存为hdf5文件格式

# keras library import  for Saving and loading model and weights

from keras.models import model_from_json
from keras.models import load_model

# serialize model to JSON
#  the keras model which is trained is defined as 'model' in this example
model_json = model.to_json()


with open("model_num.json", "w") as json_file:
    json_file.write(model_json)

# serialize weights to HDF5
model.save_weights("model_num.h5")

创建了包含模型和权重的文件“model_num.h5”和“model_num.json”

要使用相同的训练模型进行进一步测试，只需加载hdf5文件并将其用于不同数据的预测。 下面介绍如何从保存的文件加载模型

# load json and create model
json_file = open('model_num.json', 'r')

loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)

# load weights into new model
loaded_model.load_weights("model_num.h5")
print("Loaded model from disk")

model.save('model_num.hdf5')
loaded_model=load_model('model_num.hdf5')

要预测不同的数据，可以使用

loaded_model.predict_classes("your_test_data here")

---

如果您使用的是keras，则可以将其保存为hdf5文件格式并加载以进行测试

from keras.models import load_model

model.save('path where you want to save with h5 extension')

加载到以供以后使用

model = load_model('path of the h5 file which we saved using model.save')

---

如果您使用的是keras，则可以将其保存为hdf5文件格式并加载以进行测试

from keras.models import load_model

model.save('path where you want to save with h5 extension')

加载到以供以后使用

model = load_model('path of the h5 file which we saved using model.save')