如何根据权重和偏差创建 MPLClassifier？ （巨蟒 3）

Question

I am trying to create an MPLClassifier with predefined weights and biases so that I can save them to a file and then

If I train the.network like this:

import numpy as np
from sklearn.neural_network import MLPClassifier

data = np.load("data.npy")
labels = np.load("labels.npy")

clf = MLPClassifier()
clf.fit(data, labels)

np.save("weights.npy", clf.coefs_)
np.save("biases.npy", clf.intercepts_)

and then access the weights an biases like this:

import numpy as np
from sklearn.neural_network import MLPClassifier

weights = np.load("weights.npy")
biases = np.load("biases.npy")

I want to be able to create a new.network like:

clf = MLPClassifier(weights=weights, biases=biases)

Answer 1

As @Plagon commented, you can't create an MLPClassifier from weights and biases. Instead, you should import pickle and use it like:

with open("network.pkl", "wb") as network:
    pickle.dump(clf, network)

and access it like:

with open("network.pkl", "wb") as network:
    clf = pickle.load(network)

For more information on pickle you can go its documentation at https://docs.python.org/3/library/pickle.html .