我训练了Keras顺序模型，并在以后加载了它。两种模型都给出不同的精度。我遇到了类似的问题，但无法解决问题。
示例代码：加载和跟踪模型
model = gensim.models.FastText.load('abc.simple')
X,y = load_data()
Vectors = np.array(vectors(X))
X_train, X_test, y_train, y_test = train_test_split(Vectors, np.array(y),
test_size = 0.3, random_state = 0)
X_train = X_train.reshape(X_train.shape[0],100,max_tokens,1)
X_test = X_test.reshape(X_test.shape[0],100,max_tokens,1)
data for input to our model
print(X_train.shape)
model2 = train()
score = model2.evaluate(X_test, y_test, verbose=0)
print(score)
训练准确性为90％。保存模型
# Saving Model
model_json = model2.to_json()
with open("model_architecture.json", "w") as json_file:
json_file.write(model_json)
model2.save_weights("model_weights.h5")
print("Saved model to disk")
但是在我重新启动内核并刚刚加载保存的模型并在同一组数据上运行它之后，准确性降低了。
#load json and create model
json_file = open('model_architecture.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = …