Pytorch matmul 的两个参数都需要至少是 1D，但它们是 0D 和 2D

Question

我正在尝试通过图书馆学习pytorch和强化学习。我不太了解批量大小并不断收到此错误消息“matmul 的两个参数至少需要 1D，但它们是 0D 和 2D”

到目前为止，这是我的代码

import numpy as np
import gym
import torch as T
import torch.multiprocessing as mp
import torch.nn as nn
import torch.nn.functional as F
from torch.distributions import Categorical
import torch.optim as optim


class network(nn.Module):
    def __init__(self, lr, input_dims, h1_dims, h2_dims, n_actions):
        super(network, self).__init__()

        self.lr = lr
        self.input_dims = input_dims
        self.h1_dims = h1_dims
        self.h2_dims = h2_dims
        self.n_actions = n_actions

        self.h1 = nn.Linear(self.input_dims, self.h1_dims)
        self.h2 = nn.Linear(self.h1_dims, self.h2_dims)
        self.p = nn.Linear(self.h2_dims, self.n_actions)
        self.v = nn.Linear(self.h2_dims, 1)

        self.optimizer = optim.Adam(self.parameters(), lr=self.lr)
        self.device = T.device('cuda:0' if T.cuda.is_available() else 'cpu')
        self.to(self.device)

    def forward(self, observation):
        state = T.tensor(observation[0], dtype=T.float).to(self.device)

        x = F.relu(self.h1(state)) ##### here is the error ######
        x = F.relu(self.h2(x))
        v = self.v(x)
        p = F.softmax(self.p(x))

        return v, p


def choose_action(testing, observation):


        value, policy = testing.forward(observation[0])

        action_probs = T.distributions.Categorical(probs=policy)
        action = action_probs.sample()

        return action


env = gym.make('CartPole-v1')

action_spaces = env.action_space.n

network_instance = network(lr=0.005, input_dims=4, h1_dims=128,
                  h2_dims=128, n_actions=action_spaces)



for i in range(2):
    obs = env.reset()
    testing = choose_action(network_instance, obs)

    print(testing)

如何解决这个问题？？谢谢