torchmetrics下載torchmetrics源代碼下載

torchmetrics

Python

Minor patch release

下載

用於分佈式，可擴展的Pytorch應用程序的機器學習指標。

什麼是火炬器•實施度量•內置指標•文檔•社區•許可證

CI測試|中央處理器

安裝

PYPI的簡單安裝

pip install torchmetrics

其他安裝

使用conda安裝

conda install -c conda-forge torchmetrics

來自來源的PIP

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

來自檔案的pip

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

專門指標的額外依賴性：

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

安裝最新開發人員版本

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

什麼是火炬手

Torchmetrics是100多個Pytorch指標實現的集合和易於使用的API，可創建自定義指標。它提供：

標準化界面以提高可重複性
減少樣板
自動積累批次
針對分佈式培訓優化的指標
多個設備之間的自動同步

您可以將Torchmetrics與任何Pytorch型號或Pytorch Lightning一起使用，以享受其他功能，例如：

模塊指標自動放置在正確的設備上。
對閃電中記錄指標的本地支持，以減少更多的樣板。

使用火炬手

模塊指標

基於模塊的指標包含內部度量狀態（類似於Pytorch模塊的參數），它們可以自動化跨設備的積累和同步！

自動積累多批
多個設備之間的自動同步
公制算術

這可以在CPU，單個GPU或Multi-GPU上運行！

對於單個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 } " )

使用多個GPU或多個節點時，模塊度量使用率保持不變。

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 )

實施您自己的模塊指標

實施自己的指標就像對torch.nn.Module子類別一樣容易。 torchmetrics.Metric update

 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 ))

功能指標

與torch.nn類似，大多數指標都具有基於模塊的功能版本。功能版本是簡單的python函數，當輸入帶有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
)

覆蓋域和示例指標

Torchmetrics總共包含100多個指標，其中涵蓋以下域：

聲音的
分類
檢測
信息檢索
圖像
多模式（圖像文本）
名義
回歸
分割
文字

每個域可能需要一些其他依賴項，這些依賴項可以通過pip install torchmetrics[audio] ， pip install torchmetrics['image']等安裝。

其他功能

繪圖

指標的可視化對於幫助了解機器學習算法的情況很重要。 Torchmetrics具有內置的繪圖支持（使用pip install torchmetrics[visual]安裝依賴項），幾乎通過.plot方法為所有模塊化指標。只需調用該方法即可獲得任何度量的簡單可視化！

 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 )