pytorch

PyTorch深度学习快速入门教程【小土堆】 笔记

dir()、 help()

eg

help(torch.cuda.is_available)

注意要import torch
torch.cuda.is_available不能加括号

pycharm与jupyter比较

Dataset 和Dataloader

from torch.utils.data import Dataset
查看说明：
Dataset??

All datasets that represent a map from keys to data samples should subclass it.
All subclasses should overwrite :meth:__getitem__, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite
:meth:__len__, which is expected to return the size of the dataset by many
:class:~torch.utils.data.Sampler implementations and the default options
of :class:~torch.utils.data.DataLoader.

每个Dataset类都要继承它
每个Dataset类都要写一个__getitem__方法
可以写__len__方法

示例代码

文件夹目录

from torch.utils.data import Dataset
from PIL import Image
import os

class MyData(Dataset):
    def __init__(self,root_dir,label_dir):
        self.root_dir =  root_dir
        self.label_dir = label_dir
        self.path = os.path.join(self.root_dir ,self.label_dir )
        self.img_path = os.listdir(self.path )


    def __getitem__(self, idx):
        img_name=self.img_path [idx]
        img_item_path=os.path.join(self.root_dir ,self.label_dir ,img_name)
        img=Image.open(img_item_path )
        label=self.label_dir
        return img,label

    def __len__(self):
        return len(self.img_path )

#创建实例
root_dir='C:\\Users\\10755\\Desktop\\imges'
du_label_dir='都敏俊'
k_label_dir='小K'
du=MyData (root_dir,du_label_dir)
xk=MyData (root_dir,k_label_dir)

print('都教授个数：',len(du))
img,label=du[0]
img.show()
# 数据集拼接
# train_dataset=ants+bees

transform

ctrl+p 可以提示参数

from torch.utils.data import Dataset, DataLoader
from PIL import Image
import os
from torchvision import transforms

class MyData(Dataset):

    def __init__(self, root_dir, image_dir, label_dir, transform=None):
        self.root_dir = root_dir
        self.image_dir = image_dir
        self.label_dir = label_dir
        self.label_path = os.path.join(self.root_dir, self.label_dir)
        self.image_path = os.path.join(self.root_dir, self.image_dir)
        self.image_list = os.listdir(self.image_path)
        self.label_list = os.listdir(self.label_path)
        self.transform = transform
        # 因为label 和 Image文件名相同，进行一样的排序，可以保证取出的数据和label是一一对应的
        self.image_list.sort()
        self.label_list.sort()

    def __getitem__(self, idx):
        img_name = self.image_list[idx]
        label_name = self.label_list[idx]
        img_item_path = os.path.join(self.root_dir, self.image_dir, img_name)
        label_item_path = os.path.join(self.root_dir, self.label_dir, label_name)
        img = Image.open(img_item_path)
        with open(label_item_path, 'r') as f:
            label = f.readline()

        if self.transform:
            img = transform(img)


        return img, label

    def __len__(self):
        assert len(self.image_list) == len(self.label_list)
        return len(self.image_list)


transform = transforms.Compose([transforms.Resize(400), transforms.ToTensor()])
root_dir = "dataset/train"
image_ants = "ants_image"
label_ants = "ants_label"
ants_dataset = MyData(root_dir, image_ants, label_ants, transform=transform)
image_bees = "bees_image"
label_bees = "bees_label"
bees_dataset = MyData(root_dir, image_bees, label_bees, transform=transform)

tensorboard

Pytorch当中Tensorboard的使用
PyTorch 自带 TensorBoard 使用教程

示例代码

from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image

writer = SummaryWriter("logs")
# 会在当前目录下生成logs目录
image_path = "data/train/ants_image/6240329_72c01e663e.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)

writer.add_image("train", img_array, 1, dataformats='HWC')
# y = 2x
for i in range(100):
    writer.add_scalar("y=2x", 3*i, i)

writer.close()

ctrl+点击函数，可以查看函数具体情况

add_scalar

    def add_scalar(self, tag, scalar_value, global_step=None, walltime=None):
        """Add scalar data to summary.

        Args:
            tag (string): Data identifier#标题
            scalar_value (float or string/blobname): Value to save#y轴
            global_step (int): Global step value to record#X轴
            walltime (float): Optional override default walltime (time.time())#时间
              with seconds after epoch of event

add_image

    def add_image(self, tag, img_tensor, global_step=None, walltime=None, dataformats='CHW'):
        """Add image data to summary.

        Note that this requires the ``pillow`` package.

        Args:
            tag (string): Data identifier
            img_tensor (torch.Tensor, numpy.array, or string/blobname): Image data
            global_step (int): Global step value to record
            walltime (float): Optional override default walltime (time.time())
              seconds after epoch of event
        Shape:
            img_tensor: Default is :math:`(3, H, W)`. You can use ``torchvision.utils.make_grid()`` to
            convert a batch of tensor into 3xHxW format or call ``add_images`` and let us do the job.
            Tensor with :math:`(1, H, W)`, :math:`(H, W)`, :math:`(H, W, 3)` is also suitible as long as
            corresponding ``dataformats`` argument is passed. e.g. CHW, HWC, HW.

数据类型

注意一下
img_tensor (torch.Tensor, numpy.array, or string/blobname): Image data
所需的数据类型

以 PIL中的Image.open(image_path)
打开的图像是不满足要求的

可以print(type(img))
查看文件类型

转换成numpy型
np.array(img)

shape

默认为：(3, H, W)
若不是 需要加dataformats

显示

writer.add_image(“train”, img_array, 1, dataformats=‘HWC’)
train 相当于 图片窗口名
img_array输入文件
1步数

继续加载一张图：
writer.add_image(“train”, img_array, 2, dataformats=‘HWC’)

新开窗口：
writer.add_image(“小k”, img_array, 1, dataformats=‘HWC’)

打开tensorboard

pycharm terminal 输入
tensorboard --logdir=logs
注意空格不能漏，
logdir=事件文件所在文件夹名

更换打开端口：
tensorboard --logdir=logs --port=6007

自带的浏览器可能打不开
复制链接到其他览器再打开

No dashboards are active for the current data set

解决方案
若是还不行 再重新运行下代码 再打开

重复运行代码
新产生的图像会在上个图像基础上显示
解决方法：
把logs里的文件都删掉
ctrl+c关闭窗口
再重新运行 打开窗口

按住ctrl选选中多个文件