Python 为什么dot产品在斯坦福落后'；s cs231n支持向量机？

我正在看斯坦福大学cs231n的Youtube视频，并试图做练习。在执行SVM one时，我遇到了以下代码：

def svm_loss_naive(W, X, y, reg):
  """
  Structured SVM loss function, naive implementation (with loops).

  Inputs have dimension D, there are C classes, and we operate on minibatches
  of N examples.

  Inputs:
  - W: A numpy array of shape (D, C) containing weights.
  - X: A numpy array of shape (N, D) containing a minibatch of data.
  - y: A numpy array of shape (N,) containing training labels; y[i] = c means
    that X[i] has label c, where 0 <= c < C.
  - reg: (float) regularization strength

  Returns a tuple of:
  - loss as single float
  - gradient with respect to weights W; an array of same shape as W
  """
  dW = np.zeros(W.shape) # initialize the gradient as zero

  # compute the loss and the gradient
  num_classes = W.shape[1]
  num_train = X.shape[0]
  loss = 0.0
  for i in range(num_train):
    scores = X[i].dot(W) # This line
    correct_class_score = scores[y[i]]
    for j in range(num_classes):
      if j == y[i]:
        continue
      margin = scores[j] - correct_class_score + 1 # note delta = 1
      if margin > 0:
        loss += margin

---

这是在做产品xW，不是应该是Wx吗？我的意思是，

W.dot（X[I]）

因为数组的形状分别是

（D，C）

和

（N，D）

对于

W

和

X

，你不能直接取点积，而不首先将它们都转置（对于矩阵乘法，它们必须是

（C，D）·（D，N）

---

由于

X.T.dot（W.T）=W.dot（X）

，实现简单地颠倒了点积的顺序，而不是对每个数组进行变换。实际上，这取决于输入的排列方式。在这种情况下（有些随意）我们决定以更直观的方式安排样本和特征，而不是将dot产品作为

x·W

很好的解释，尽管我认为应该是

xᵀ.点（Wᵀ) == [W.dot（X）]ᵀ。
scores = X[i].dot(W)