催化剂。使用 PyTorch 加速深度学习研发。

导航

项目链接

统计数据

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Meta

License: Apache Software License (Apache License 2.0)

作者: Sergey Kolesnikov

Tags Machine Learning, Distributed Computing, Deep Learning, Reinforcement Learning, Computer Vision, Natural Language Processing, Recommendation Systems, Information Retrieval, PyTorch

Requires: Python >=3.7.0

Maintainers

Avatar for scitator from gravatar.com scitator

分类

项目描述

催化剂标志

加速深度学习研发

代码因子 皮皮版 文档 码头工人 PyPI 状态

推特 电报 松弛 Github 贡献者

代码风格 文档 催化剂 集成

Python Python Python

操作系统 操作系统 操作系统

Catalyst 是用于深度学习研究和开发的 PyTorch 框架。它专注于可重复性、快速实验和代码库重用，因此您可以创建新的东西而不是编写另一个训练循环。
打破循环——使用催化剂！

2021 年 PyTorch 生态系统日的催化剂

催化剂海报

2021 年 PyTorch 开发者日的催化剂

催化剂海报

入门

pip install -U catalyst

import os
from torch import nn, optim
from torch.utils.data import DataLoader
from catalyst import dl, utils
from catalyst.contrib.datasets import MNIST

model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10))
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.02)
loaders = {
    "train": DataLoader(MNIST(os.getcwd(), train=True), batch_size=32),
    "valid": DataLoader(MNIST(os.getcwd(), train=False), batch_size=32),
}

runner = dl.SupervisedRunner(
    input_key="features", output_key="logits", target_key="targets", loss_key="loss"
)

# model training
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    loaders=loaders,
    num_epochs=1,
    callbacks=[
        dl.AccuracyCallback(input_key="logits", target_key="targets", topk=(1, 3, 5)),
        dl.PrecisionRecallF1SupportCallback(input_key="logits", target_key="targets"),
    ],
    logdir="./logs",
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
    verbose=True,
)

# model evaluation
metrics = runner.evaluate_loader(
    loader=loaders["valid"],
    callbacks=[dl.AccuracyCallback(input_key="logits", target_key="targets", topk=(1, 3, 5))],
)

# model inference
for prediction in runner.predict_loader(loader=loaders["valid"]):
    assert prediction["logits"].detach().cpu().numpy().shape[-1] == 10

# model post-processing
model = runner.model.cpu()
batch = next(iter(loaders["valid"]))[0]
utils.trace_model(model=model, batch=batch)
utils.quantize_model(model=model)
utils.prune_model(model=model, pruning_fn="l1_unstructured", amount=0.8)
utils.onnx_export(model=model, batch=batch, file="./logs/mnist.onnx", verbose=True)

分步指南

  1. Start with Catalyst — 用于加速深度学习研发的 PyTorch 框架。
  2. 尝试笔记本教程或检查最小示例以进行第一次深入研究。
  3. 阅读包含用例和指南的博客文章。
  4. 通过我们的“使用 Catalyst 进行深度学习”课程学习机器学习。
  5. 最后，如果您想与团队和贡献者聊天，请加入我们的 slack 。

目录

概述

Catalyst 只需几行代码即可帮助您实现紧凑但功能齐全的深度学习管道。您可以在没有样板的情况下获得包含指标、提前停止、模型检查点和其他功能的训练循环。

安装

通用安装：

pip install -U catalyst
专用版本，可能适用额外要求 

pip install catalyst[ml]         # installs ML-based Catalyst
pip install catalyst[cv]         # installs CV-based Catalyst
# master version installation
pip install git+https://github.com/catalyst-team/catalyst@master --upgrade
# all available extensions are listed here:
# https://github.com/catalyst-team/catalyst/blob/master/setup.py

Catalyst 兼容：Python 3.7+。PyTorch 1.4+。
在 Ubuntu 16.04/18.04/20.04、macOS 10.15、Windows 10 和适用于 Linux 的 Windows 子系统上测试。

文档

最小的例子

CustomRunner – PyTorch for 循环分解 

import os
from torch import nn, optim
from torch.nn import functional as F
from torch.utils.data import DataLoader
from catalyst import dl, metrics
from catalyst.contrib.datasets import MNIST

model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10))
optimizer = optim.Adam(model.parameters(), lr=0.02)

train_data = MNIST(os.getcwd(), train=True)
valid_data = MNIST(os.getcwd(), train=False)
loaders = {
    "train": DataLoader(train_data, batch_size=32),
    "valid": DataLoader(valid_data, batch_size=32),
}

class CustomRunner(dl.Runner):
    def predict_batch(self, batch):
        # model inference step
        return self.model(batch[0].to(self.engine.device))

    def on_loader_start(self, runner):
        super().on_loader_start(runner)
        self.meters = {
            key: metrics.AdditiveMetric(compute_on_call=False)
            for key in ["loss", "accuracy01", "accuracy03"]
        }

    def handle_batch(self, batch):
        # model train/valid step
        # unpack the batch
        x, y = batch
        # run model forward pass
        logits = self.model(x)
        # compute the loss
        loss = F.cross_entropy(logits, y)
        # compute the metrics
        accuracy01, accuracy03 = metrics.accuracy(logits, y, topk=(1, 3))
        # log metrics
        self.batch_metrics.update(
            {"loss": loss, "accuracy01": accuracy01, "accuracy03": accuracy03}
        )
        for key in ["loss", "accuracy01", "accuracy03"]:
            self.meters[key].update(self.batch_metrics[key].item(), self.batch_size)
        # run model backward pass
        if self.is_train_loader:
            self.engine.backward(loss)
            self.optimizer.step()
            self.optimizer.zero_grad()

    def on_loader_end(self, runner):
        for key in ["loss", "accuracy01", "accuracy03"]:
            self.loader_metrics[key] = self.meters[key].compute()[0]
        super().on_loader_end(runner)

runner = CustomRunner()
# model training
runner.train(
    model=model,
    optimizer=optimizer,
    loaders=loaders,
    logdir="./logs",
    num_epochs=5,
    verbose=True,
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
)
# model inference
for logits in runner.predict_loader(loader=loaders["valid"]):
    assert logits.detach().cpu().numpy().shape[-1] == 10

ML - 线性回归 

import torch
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# data
num_samples, num_features = int(1e4), int(1e1)
X, y = torch.rand(num_samples, num_features), torch.rand(num_samples)
dataset = TensorDataset(X, y)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

# model, criterion, optimizer, scheduler
model = torch.nn.Linear(num_features, 1)
criterion = torch.nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters())
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [3, 6])

# model training
runner = dl.SupervisedRunner()
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    logdir="./logdir",
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
    num_epochs=8,
    verbose=True,
)

ML - 多类分类 

import torch
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# sample data
num_samples, num_features, num_classes = int(1e4), int(1e1), 4
X = torch.rand(num_samples, num_features)
y = (torch.rand(num_samples,) * num_classes).to(torch.int64)

# pytorch loaders
dataset = TensorDataset(X, y)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

# model, criterion, optimizer, scheduler
model = torch.nn.Linear(num_features, num_classes)
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters())
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [2])

# model training
runner = dl.SupervisedRunner(
    input_key="features", output_key="logits", target_key="targets", loss_key="loss"
)
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    logdir="./logdir",
    num_epochs=3,
    valid_loader="valid",
    valid_metric="accuracy03",
    minimize_valid_metric=False,
    verbose=True,
    callbacks=[
        dl.AccuracyCallback(input_key="logits", target_key="targets", num_classes=num_classes),
        # uncomment for extra metrics:
        # dl.PrecisionRecallF1SupportCallback(
        #     input_key="logits", target_key="targets", num_classes=num_classes
        # ),
        # dl.AUCCallback(input_key="logits", target_key="targets"),
        # catalyst[ml] required ``pip install catalyst[ml]``
        # dl.ConfusionMatrixCallback(
        #     input_key="logits", target_key="targets", num_classes=num_classes
        # ),
    ],
)

ML - 多标签分类 

import torch
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# sample data
num_samples, num_features, num_classes = int(1e4), int(1e1), 4
X = torch.rand(num_samples, num_features)
y = (torch.rand(num_samples, num_classes) > 0.5).to(torch.float32)

# pytorch loaders
dataset = TensorDataset(X, y)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

# model, criterion, optimizer, scheduler
model = torch.nn.Linear(num_features, num_classes)
criterion = torch.nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters())
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [2])

# model training
runner = dl.SupervisedRunner(
    input_key="features", output_key="logits", target_key="targets", loss_key="loss"
)
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    logdir="./logdir",
    num_epochs=3,
    valid_loader="valid",
    valid_metric="accuracy01",
    minimize_valid_metric=False,
    verbose=True,
    callbacks=[
        dl.BatchTransformCallback(
            transform=torch.sigmoid,
            scope="on_batch_end",
            input_key="logits",
            output_key="scores"
        ),
        dl.AUCCallback(input_key="scores", target_key="targets"),
        # uncomment for extra metrics:
        # dl.MultilabelAccuracyCallback(input_key="scores", target_key="targets", threshold=0.5),
        # dl.MultilabelPrecisionRecallF1SupportCallback(
        #     input_key="scores", target_key="targets", threshold=0.5
        # ),
    ]
)

ML - 多头分类 

import torch
from torch import nn