python - PyTorch:传递 numpy 数组以进行权重初始化

Question

我想用 np 数组初始化 RNN 的参数。

在下面的例子中，我想通过 w到rnn的参数.我知道 pytorch 提供了许多初始化方法，如 Xavier、uniform 等，但是有没有办法通过传递 numpy 数组来初始化参数？

import numpy as np
import torch as nn
rng = np.random.RandomState(313)
w = rng.randn(input_size, hidden_size).astype(np.float32)

rnn = nn.RNN(input_size, hidden_size, num_layers)

Answer 1

首先，让我们注意 nn.RNN有多个权重变量，c.f. documentation :

Variables:

• weight_ih_l[k] – the learnable input-hidden weights of the k-th layer, of shape (hidden_size * input_size) for k = 0. Otherwise, the shape is (hidden_size * hidden_size)
• weight_hh_l[k] – the learnable hidden-hidden weights of the k-th layer, of shape (hidden_size * hidden_size)
• bias_ih_l[k] – the learnable input-hidden bias of the k-th layer, of shape (hidden_size)
• bias_hh_l[k] – the learnable hidden-hidden bias of the k-th layer, of shape (hidden_size)

现在，这些变量中的每一个( Parameter 实例)都是您的 nn.RNN 的属性。实例。您可以通过两种方式访问​​和编辑它们，如下所示:

方案一:访问所有RNN Parameter按名称的属性( rnn.weight_hh_lK 、 rnn.weight_ih_lK 等):

import torch
from torch import nn
import numpy as np

input_size, hidden_size, num_layers = 3, 4, 2
use_bias = True
rng = np.random.RandomState(313)

rnn = nn.RNN(input_size, hidden_size, num_layers, bias=use_bias)

def set_nn_parameter_data(layer, parameter_name, new_data):
    param = getattr(layer, parameter_name)
    param.data = new_data

for i in range(num_layers):
    weights_hh_layer_i = rng.randn(hidden_size, hidden_size).astype(np.float32)
    weights_ih_layer_i = rng.randn(hidden_size, hidden_size).astype(np.float32)
    set_nn_parameter_data(rnn, "weight_hh_l{}".format(i), 
                          torch.from_numpy(weights_hh_layer_i))
    set_nn_parameter_data(rnn, "weight_ih_l{}".format(i), 
                          torch.from_numpy(weights_ih_layer_i))

    if use_bias:
        bias_hh_layer_i = rng.randn(hidden_size).astype(np.float32)
        bias_ih_layer_i = rng.randn(hidden_size).astype(np.float32)
        set_nn_parameter_data(rnn, "bias_hh_l{}".format(i), 
                              torch.from_numpy(bias_hh_layer_i))
        set_nn_parameter_data(rnn, "bias_ih_l{}".format(i), 
                              torch.from_numpy(bias_ih_layer_i))

方案二:访问所有RNN Parameter属性通过 rnn.all_weights列表属性:

import torch
from torch import nn
import numpy as np

input_size, hidden_size, num_layers = 3, 4, 2
use_bias = True
rng = np.random.RandomState(313)

rnn = nn.RNN(input_size, hidden_size, num_layers, bias=use_bias)

for i in range(num_layers):
    weights_hh_layer_i = rng.randn(hidden_size, hidden_size).astype(np.float32)
    weights_ih_layer_i = rng.randn(hidden_size, hidden_size).astype(np.float32)
    rnn.all_weights[i][0].data = torch.from_numpy(weights_ih_layer_i)
    rnn.all_weights[i][1].data = torch.from_numpy(weights_hh_layer_i)

    if use_bias:
        bias_hh_layer_i = rng.randn(hidden_size).astype(np.float32)
        bias_ih_layer_i = rng.randn(hidden_size).astype(np.float32)
        rnn.all_weights[i][2].data = torch.from_numpy(bias_ih_layer_i)
        rnn.all_weights[i][3].data = torch.from_numpy(bias_hh_layer_i)