比较与torch.optim.AdaMax的差异

class torch.optim.AdaMax(
    params,
    lr=0.002,
    betas=(0.9, 0.999),
    eps=1e-08,
    weight_decay=0
)

class mindspore.nn.AdaMax(
    params,
    learning_rate=0.001,
    beta1=0.9,
    beta2=0.999,
    eps=1e-08,
    weight_decay=0.0,
    loss_scale=1.0
)

# MindSpore
import mindspore
from mindspore import nn

net = nn.Dense(2, 3)
optimizer = nn.AdaMax(net.trainable_params())
criterion = nn.MAELoss(reduction="mean")

def forward_fn(data, label):
    logits = net(data)
    loss = criterion(logits, label)
    return loss, logits

grad_fn = mindspore.value_and_grad(forward_fn, None, optimizer.parameters, has_aux=True)

def train_step(data, label):
    (loss, _), grads = grad_fn(data, label)
    optimizer(grads)
    return loss

# PyTorch
import torch

model = torch.nn.Linear(2, 3)
criterion = torch.nn.L1Loss(reduction='mean')
optimizer = torch.optim.AdaMax(model.parameters())
def train_step(data, label):
    optimizer.zero_grad()
    output = model(data)
    loss = criterion(output, label)
    loss.backward()
    optimizer.step()