fastai_minima

一个与Pytorch一起工作的fastai最小版本，包含必要的最基本组件

#all_slow

安装

pip install fastai_minima

如何使用

这个库旨在仅引入从fastai需要的最小功能，以与原始Pytorch一起工作。这包括

• 学习者
• 回调
• 优化器
• 数据加载器（但不包括DataBlock）
• 指标

以下是基于我的Pytorch到fastai，架起桥梁文章的一个非常简单的示例

import torch
import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))])

dset_train = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)

dset_test = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)

trainloader = torch.utils.data.DataLoader(dset_train, batch_size=4,
                                          shuffle=True, num_workers=2)
testloader = torch.utils.data.DataLoader(dset_test, batch_size=4,
                                         shuffle=False, num_workers=2)

Files already downloaded and verified
Files already downloaded and verified

import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

criterion = nn.CrossEntropyLoss()

from torch import optim
from fastai_minima.optimizer import OptimWrapper
from fastai_minima.learner import Learner, DataLoaders
from fastai_minima.callback.training import CudaCallback, ProgressCallback

def opt_func(params, **kwargs): return OptimWrapper(optim.SGD(params, **kwargs))

dls = DataLoaders(trainloader, testloader)

learn = Learner(dls, Net(), loss_func=criterion, opt_func=opt_func)

# To use the GPU, do 
# learn = Learner(dls, Net(), loss_func=criterion, opt_func=opt_func, cbs=[CudaCallback()])

learn.fit(2, lr=0.001)

/mnt/d/lib/python3.7/site-packages/torch/autograd/__init__.py:132: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at  /pytorch/c10/cuda/CUDAFunctions.cpp:100.)
  allow_unreachable=True)  # allow_unreachable flag

如果您想进行差异学习率，在创建用于传递给fastai的Learner的splitter时，应使用convert_params使其与Pytorch优化器兼容

def splitter(m): return convert_params([[m.a], [m.b]])

learn = Learner(..., splitter=splitter)