在custom weight initialization
中实现PyTorch
方法的正确方法是什么?
我相信我无法直接在'torch.nn.init`中添加任何方法,但希望使用自己的专有方法来初始化模型的权重。
答案 0 :(得分:5)
您可以定义一种根据每个图层初始化权重的方法:
def weights_init(m):
classname = m.__class__.__name__
if classname.find('Conv2d') != -1:
m.weight.data.normal_(0.0, 0.02)
elif classname.find('BatchNorm') != -1:
m.weight.data.normal_(1.0, 0.02)
m.bias.data.fill_(0)
然后将其应用于您的网络:
model = create_your_model()
model.apply(weights_init)
答案 1 :(得分:1)
请参阅https://discuss.pytorch.org/t/how-to-initialize-weights-bias-of-rnn-lstm-gru/2879/2以供参考。
您可以
weight_dict = net.state_dict()
new_weight_dict = {}
for param_key in state_dict:
# custom initialization in new_weight_dict,
# You can initialize partially i.e only some of the variables and let others stay as it is
weight_dict.update(new_weight_dict)
net.load_state_dict(new_weight_dict)