Theano - 保存和加载模型参数

Theano 学习资源较少

不建议使用theano做pre-train

资源

theano学习之模型的保存和提取_水月清的博客-CSDN博客_theano 保存模型

Save 保存 提取 - Theano | 莫烦Python

save model

# save model
with open('save/model.pickle', 'wb') as file:
    model = [w.get_value(), b.get_value()]
    pickle.dump(model, file)
    print(model[0][:10])
    print("accuracy:", compute_accuracy(D[1], predict(D[0])))

"""
[-0.15707296  0.14590665 -0.08451091 -0.12594476 -0.13424085 -0.33887753
  0.12650858  0.20702686  0.0549835   0.29920542]
accuracy: 1.0
"""

load model

# load model
with open('save/model.pickle', 'rb') as file:
    model = pickle.load(file)
    w.set_value(model[0])
    b.set_value(model[1])
    print(w.get_value()[:10])
    print("accuracy:", compute_accuracy(D[1], predict(D[0])))
    
"""
[-0.15707296  0.14590665 -0.08451091 -0.12594476 -0.13424085 -0.33887753
  0.12650858  0.20702686  0.0549835   0.29920542]
accuracy: 1.0
"""