TensorFlow 到 PyTorch

Question

我正在将 TensorFlow 代码转换为 PyTorch 代码。
下面几行是我还不能解决的问题。
我对 PyTorch 不熟悉，所以在 PyTorch 库中找到匹配的方法并不容易。
谁能帮帮我？
p.s. alpha的形状是(batch, N)。

alpha_cumsum = tf.cumsum(alpha, axis = 1)
len_batch = tf.shape(alpha_cumsum)[0]
rand_prob = tf.random_uniform(shape = [len_batch, 1], minval = 0., maxval = 1.)
alpha_relu = tf.nn.relu(rand_prob - alpha_cumsum)
alpha_index = tf.count_nonzero(alpha_relu, 1)
alpha_hard  = tf.one_hot(alpha_index, len(a))

Answer 1

我已经把你所有的函数都放在了相应的 pytorch 函数之后。大多数都是同名并放在 pytorch 文档中 (https://pytorch.org/docs/stable/index.html)

tf.cumsum(alpha, axis = 1)  
torch.cumsum(alpha, dim=1)

tf.shape(alpha_cumsum)[0]
alpha_cumsum.shape[0]

tf.random_uniform(shape = [len_batch, 1], minval = 0., maxval = 1.)
torch.rand([len_batch,1])

tf.nn.relu(rand_prob - alpha_cumsum)
torch.nn.functional.relu(rand_prob - alpha_cumsum)

tf.count_nonzero(alpha_relu, 1)
torch.count_nonzero(alpha_relu, dim=1)

tf.one_hot(alpha_index, len(a))
torch.nn.functional.one_hot(alpha_index, len(a)) # assuming len(a) is number of classes