torchmetrics下载torchmetrics源代码下载

torchmetrics

Python

Minor patch release

下载

用于分布式，可扩展的Pytorch应用程序的机器学习指标。

什么是火炬器•实施度量•内置指标•文档•社区•许可证

CI测试|中央处理器

安装

PYPI的简单安装

pip install torchmetrics

其他安装

使用conda安装

conda install -c conda-forge torchmetrics

来自来源的PIP

 # with git
pip install git+https://github.com/Lightning-AI/torchmetrics.git@release/stable

来自档案的pip

pip install https://github.com/Lightning-AI/torchmetrics/archive/refs/heads/release/stable.zip

专门指标的额外依赖性：

pip install torchmetrics[audio]
pip install torchmetrics[image]
pip install torchmetrics[text]
pip install torchmetrics[all]  # install all of the above

安装最新开发人员版本

pip install https://github.com/Lightning-AI/torchmetrics/archive/master.zip

什么是火炬手

Torchmetrics是100多个Pytorch指标实现的集合和易于使用的API，可创建自定义指标。它提供：

标准化界面以提高可重复性
减少样板
自动积累批次
针对分布式培训优化的指标
多个设备之间的自动同步

您可以将Torchmetrics与任何Pytorch型号或Pytorch Lightning一起使用，以享受其他功能，例如：

模块指标自动放置在正确的设备上。
对闪电中记录指标的本地支持，以减少更多的样板。

使用火炬手

模块指标

基于模块的指标包含内部度量状态（类似于Pytorch模块的参数），它们可以自动化跨设备的积累和同步！

自动积累多批
多个设备之间的自动同步
公制算术

这可以在CPU，单个GPU或Multi-GPU上运行！

对于单个GPU/CPU案例：

 import torch

# import our library
import torchmetrics

# initialize metric
metric = torchmetrics . classification . Accuracy ( task = "multiclass" , num_classes = 5 )

# move the metric to device you want computations to take place
device = "cuda" if torch . cuda . is_available () else "cpu"
metric . to ( device )

n_batches = 10
for i in range ( n_batches ):
    # simulate a classification problem
    preds = torch . randn ( 10 , 5 ). softmax ( dim = - 1 ). to ( device )
    target = torch . randint ( 5 , ( 10 ,)). to ( device )

    # metric on current batch
    acc = metric ( preds , target )
    print ( f"Accuracy on batch { i } : { acc } " )

# metric on all batches using custom accumulation
acc = metric . compute ()
print ( f"Accuracy on all data: { acc } " )

使用多个GPU或多个节点时，模块度量使用率保持不变。

使用DDP的示例

 import os
import torch
import torch . distributed as dist
import torch . multiprocessing as mp
from torch import nn
from torch . nn . parallel import DistributedDataParallel as DDP
import torchmetrics


def metric_ddp ( rank , world_size ):
    os . environ [ "MASTER_ADDR" ] = "localhost"
    os . environ [ "MASTER_PORT" ] = "12355"

    # create default process group
    dist . init_process_group ( "gloo" , rank = rank , world_size = world_size )

    # initialize model
    metric = torchmetrics . classification . Accuracy ( task = "multiclass" , num_classes = 5 )

    # define a model and append your metric to it
    # this allows metric states to be placed on correct accelerators when
    # .to(device) is called on the model
    model = nn . Linear ( 10 , 10 )
    model . metric = metric
    model = model . to ( rank )

    # initialize DDP
    model = DDP ( model , device_ids = [ rank ])

    n_epochs = 5
    # this shows iteration over multiple training epochs
    for n in range ( n_epochs ):
        # this will be replaced by a DataLoader with a DistributedSampler
        n_batches = 10
        for i in range ( n_batches ):
            # simulate a classification problem
            preds = torch . randn ( 10 , 5 ). softmax ( dim = - 1 )
            target = torch . randint ( 5 , ( 10 ,))

            # metric on current batch
            acc = metric ( preds , target )
            if rank == 0 :  # print only for rank 0
                print ( f"Accuracy on batch { i } : { acc } " )

        # metric on all batches and all accelerators using custom accumulation
        # accuracy is same across both accelerators
        acc = metric . compute ()
        print ( f"Accuracy on all data: { acc } , accelerator rank: { rank } " )

        # Resetting internal state such that metric ready for new data
        metric . reset ()

    # cleanup
    dist . destroy_process_group ()


if __name__ == "__main__" :
    world_size = 2  # number of gpus to parallelize over
    mp . spawn ( metric_ddp , args = ( world_size ,), nprocs = world_size , join = True )

实施您自己的模块指标

实施自己的指标就像对torch.nn.Module子类别一样容易。 torchmetrics.Metric update compute

 import torch
from torchmetrics import Metric


class MyAccuracy ( Metric ):
    def __init__ ( self ):
        # remember to call super
        super (). __init__ ()
        # call `self.add_state`for every internal state that is needed for the metrics computations
        # dist_reduce_fx indicates the function that should be used to reduce
        # state from multiple processes
        self . add_state ( "correct" , default = torch . tensor ( 0 ), dist_reduce_fx = "sum" )
        self . add_state ( "total" , default = torch . tensor ( 0 ), dist_reduce_fx = "sum" )

    def update ( self , preds : torch . Tensor , target : torch . Tensor ) -> None :
        # extract predicted class index for computing accuracy
        preds = preds . argmax ( dim = - 1 )
        assert preds . shape == target . shape
        # update metric states
        self . correct += torch . sum ( preds == target )
        self . total += target . numel ()

    def compute ( self ) -> torch . Tensor :
        # compute final result
        return self . correct . float () / self . total


my_metric = MyAccuracy ()
preds = torch . randn ( 10 , 5 ). softmax ( dim = - 1 )
target = torch . randint ( 5 , ( 10 ,))

print ( my_metric ( preds , target ))

功能指标

与torch.nn类似，大多数指标都具有基于模块的功能版本。功能版本是简单的python函数，当输入带有torch.tensor。

 import torch

# import our library
import torchmetrics

# simulate a classification problem
preds = torch . randn ( 10 , 5 ). softmax ( dim = - 1 )
target = torch . randint ( 5 , ( 10 ,))

acc = torchmetrics . functional . classification . multiclass_accuracy (
    preds , target , num_classes = 5
)

覆盖域和示例指标

Torchmetrics总共包含100多个指标，其中涵盖以下域：

声音的
分类
检测
信息检索
图像
多模式（图像文本）
名义
回归
分割
文本

每个域可能需要一些其他依赖项，这些依赖项可以通过pip install torchmetrics[audio] ， pip install torchmetrics['image']等安装。

其他功能

绘图

指标的可视化对于帮助了解机器学习算法的情况很重要。 Torchmetrics具有内置的绘图支持（使用pip install torchmetrics[visual]安装依赖项），几乎通过.plot方法为所有模块化指标。只需调用该方法即可获得任何度量的简单可视化！

 import torch
from torchmetrics . classification import MulticlassAccuracy , MulticlassConfusionMatrix

num_classes = 3

# this will generate two distributions that comes more similar as iterations increase
w = torch . randn ( num_classes )
target = lambda it : torch . multinomial (( it * w ). softmax ( dim = - 1 ), 100 , replacement = True )
preds = lambda it : torch . multinomial (( it * w ). softmax ( dim = - 1 ), 100 , replacement = True )

acc = MulticlassAccuracy ( num_classes = num_classes , average = "micro" )
acc_per_class = MulticlassAccuracy ( num_classes = num_classes , average = None )
confmat = MulticlassConfusionMatrix ( num_classes = num_classes )

# plot single value
for i in range ( 5 ):
    acc_per_class . update ( preds ( i ), target ( i ))
    confmat . update ( preds ( i ), target ( i ))
fig1 , ax1 = acc_per_class . plot ()
fig2 , ax2 = confmat . plot ()

# plot multiple values
values = []
for i in range ( 10 ):
    values . append ( acc ( preds ( i ), target ( i )))
fig3 , ax3 = acc . plot ( values )