「深度学习一遍过」必修16：Tensorboard与Transforms

本文链接：https://blog.csdn.net/it_charge/article/details/119561638

此篇博客详细介绍了如何使用Tensorboard进行可视化，包括直线绘制、图片展示及多图片滑动查看。此外，还涵盖了PyTorch中常用的Transforms及其应用，如图片转Tensor和归一化操作。适合深度学习初学者和进阶者查阅。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

本专栏用于记录关于深度学习的笔记，不光方便自己复习与查阅，同时也希望能给您解决一些关于深度学习的相关问题，并提供一些微不足道的人工神经网络模型设计思路。
专栏地址：「深度学习一遍过」必修篇

1 Tensorboard

1.1 初始化

终端键入

tensorboard --logdir=*** --port=****

$--logdir=$ 事件文件所在文件夹名
$--port=$ 路径后缀数字名（可自定义）

1.2 使用实例

1.2.1 画一条直线

from tensorboardX import SummaryWriter

writer = SummaryWriter('logs')

for i in range(100):
    writer.add_scalar('y=x', i, i)

writer.close()

tensorboard --logdir=logs --port=6007

1.2.2 查看一张图片

import numpy as np
from PIL import Image
from tensorboardX import SummaryWriter

writer = SummaryWriter('logs')

img_path = r'H:\girl.jpeg'
img_PIL = Image.open(img_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)

writer.add_image('test', img_array, 1, dataformats='HWC')

writer.close()

1.2.3 滑动查看多张图片

在 $1.2.2$ 基础上再在 $IDE$ 上运行下列代码：

import numpy as np
from PIL import Image
from tensorboardX import SummaryWriter

writer = SummaryWriter('logs')

img_path = r'H:girlfriend.jpg'
img_PIL = Image.open(img_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)

writer.add_image('test', img_array, 1, dataformats='HWC')

writer.close()

2 Transforms

2.1 常见的Transforms

输入 --> $PIL$ --> $Image.open()$
输出 --> $tensor$ --> $ToTensor()$
作用 --> $narrays$ --> $cv.imread()$

2.2 Transforms该如何使用

from PIL import Image
from torchvision import transforms

img_path = 'E:/img.PNG'
img = Image.open(img_path)

tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)

print(tensor_img)

from PIL import Image
from tensorboardX import SummaryWriter
from torchvision import transforms

writer = SummaryWriter('logs')
img_path = r'female.jpg'
img = Image.open(img_path)
print(img)

# ToTensor
trans_tensors = transforms.ToTensor()
img_tensor = trans_tensors(img)
writer.add_image('ToTensor', img_tensor)

# Normalize
print(img_tensor[0][0][0])
trans_norm = transforms.Normalize([0.5,0.5,0.5], [0.5,0.5,0.5])
img_norm = trans_norm(img_tensor)
print(img_norm[0][0][0])
writer.add_image('Normalize', img_norm)

writer.close()