import cPickle
as pickle
sys.setrecursionlimit(
10000)
with open(
"model_file",
'wb')
as f:
pickle.dump(nolearnnet , f, -
1)
但是,如果据说在GPU上训练的神经网络要用读取出来用CPU做计算,以上方法不行。而应该使用更暴力的方法:
weights = lasagne
.layers.get_all_param_values(nolearnnet
.get_all_layers()[-
1])
这样就可以用numpy.savez()存储和读取这些值了。当你需要把他们赋给一个网络时,可以采用:
lasagne
.layers.set_all_param_values(nolearnnet2
.get_all_layers()[-
1], weights)
转载请注明原文地址: https://ju.6miu.com/read-9335.html