PyTorch 中的累积梯度

https://stackoverflow.com/questions/62067400/understanding-accumulated-gradients-in-pytorch

有一个小的计算图,两次前向梯度累积的结果,可以看到梯度是严格相等的。


代码:

复制代码
import numpy as np
import torch


class ExampleLinear(torch.nn.Module):

    def __init__(self):
        super().__init__()
        # Initialize the weight at 1
        self.weight = torch.nn.Parameter(torch.Tensor([1]).float(),
                                         requires_grad=True)

    def forward(self, x):
        return self.weight * x


model = ExampleLinear()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)


def calculate_loss(x: torch.Tensor) -> torch.Tensor:
    y = 2 * x
    y_hat = model(x)
    temp1 = (y - y_hat)
    temp2 = temp1**2
    return temp2


# With mulitple batches of size 1
batches = [torch.tensor([4.0]), torch.tensor([2.0])]

optimizer.zero_grad()
for i, batch in enumerate(batches):
    # The loss needs to be scaled, because the mean should be taken across the whole
    # dataset, which requires the loss to be divided by the number of batches.
    temp2 = calculate_loss(batch)
    loss = temp2 / len(batches)
    loss.backward()
    print(f"Batch size 1 (batch {i}) - grad: {model.weight.grad}")
    print(f"Batch size 1 (batch {i}) - weight: {model.weight}")
    print("="*50)

# Updating the model only after all batches
optimizer.step()
print(f"Batch size 1 (final) - grad: {model.weight.grad}")
print(f"Batch size 1 (final) - weight: {model.weight}")

运行结果

复制代码
Batch size 1 (batch 0) - grad: tensor([-16.])
Batch size 1 (batch 0) - weight: Parameter containing:
tensor([1.], requires_grad=True)
==================================================
Batch size 1 (batch 1) - grad: tensor([-20.])
Batch size 1 (batch 1) - weight: Parameter containing:
tensor([1.], requires_grad=True)
==================================================
Batch size 1 (final) - grad: tensor([-20.])
Batch size 1 (final) - weight: Parameter containing:
tensor([1.2000], requires_grad=True)

然而,如果训练一个真实的模型,结果没有这么理想,比如训练一个bert,𝐵=8,𝑁=1:没有梯度累积(累积每一步),

𝐵=2,𝑁=4:梯度累积(每 4 步累积一次)

使用带有梯度累积的 Batch Normalization 通常效果不佳,原因很简单,因为 BatchNorm 统计数据无法累积。更好的解决方案是使用 Group Normalization 而不是 BatchNorm。

https://ai.stackexchange.com/questions/21972/what-is-the-relationship-between-gradient-accumulation-and-batch-size

相关推荐
我有医保我先冲17 分钟前
AI大模型与人工智能的深度融合:重构医药行业数字化转型的底层逻辑
人工智能·重构
pen-ai41 分钟前
【NLP】15. NLP推理方法详解 --- 动态规划:序列标注,语法解析,共同指代
人工智能·自然语言处理·动态规划
Chaos_Wang_1 小时前
NLP高频面试题(二十九)——大模型解码常见参数解析
人工智能·自然语言处理
liuhaoran___1 小时前
解释区块链技术的应用场景和优势
python
独好紫罗兰1 小时前
洛谷题单2-P5712 【深基3.例4】Apples-python-流程图重构
开发语言·python·算法
Acrelhuang1 小时前
8.3MW屋顶光伏+光储协同:上海汽车变速器低碳工厂的能源革命-安科瑞黄安南
大数据·数据库·人工智能·物联网·数据库开发
区块链蓝海1 小时前
沉浸式体验测评|AI Ville:我在Web3小镇“生活”了一周
人工智能·web3·生活
东方佑1 小时前
深度解析Python-PPTX库:逐层解析PPT内容与实战技巧
开发语言·python·powerpoint
whaosoft-1431 小时前
51c自动驾驶~合集15
人工智能