Pytorch可视化的几种实现方法
作者:_Be_Water_ 时间:2023-06-11 17:44:57
目录
一,利用 tensorboardX 可视化网络结构
二,利用 vistom 可视化
三,利用pytorchviz可视化网络结构
一,利用 tensorboardX 可视化网络结构
参考 https://github.com/lanpa/tensorboardX
支持scalar, image, figure, histogram, audio, text, graph, onnx_graph, embedding, pr_curve and video summaries.
例子要求tensorboardX>=1.2 and pytorch>=0.4
安装
pip install tensorboardX
或 pip install git+https://github.com/lanpa/tensorboardX
例子
# demo.py
import torch
import torchvision.utils as vutils
import numpy as np
import torchvision.models as models
from torchvision import datasets
from tensorboardX import SummaryWriter
resnet18 = models.resnet18(False)
writer = SummaryWriter()
sample_rate = 44100
freqs = [262, 294, 330, 349, 392, 440, 440, 440, 440, 440, 440]
for n_iter in range(100):
dummy_s1 = torch.rand(1)
dummy_s2 = torch.rand(1)
# data grouping by `slash`
writer.add_scalar('data/scalar1', dummy_s1[0], n_iter)
writer.add_scalar('data/scalar2', dummy_s2[0], n_iter)
writer.add_scalars('data/scalar_group', {'xsinx': n_iter * np.sin(n_iter),
'xcosx': n_iter * np.cos(n_iter),
'arctanx': np.arctan(n_iter)}, n_iter)
dummy_img = torch.rand(32, 3, 64, 64) # output from network
if n_iter % 10 == 0:
x = vutils.make_grid(dummy_img, normalize=True, scale_each=True)
writer.add_image('Image', x, n_iter)
dummy_audio = torch.zeros(sample_rate * 2)
for i in range(x.size(0)):
# amplitude of sound should in [-1, 1]
dummy_audio[i] = np.cos(freqs[n_iter // 10] * np.pi * float(i) / float(sample_rate))
writer.add_audio('myAudio', dummy_audio, n_iter, sample_rate=sample_rate)
writer.add_text('Text', 'text logged at step:' + str(n_iter), n_iter)
for name, param in resnet18.named_parameters():
writer.add_histogram(name, param.clone().cpu().data.numpy(), n_iter)
# needs tensorboard 0.4RC or later
writer.add_pr_curve('xoxo', np.random.randint(2, size=100), np.random.rand(100), n_iter)
dataset = datasets.MNIST('mnist', train=False, download=True)
images = dataset.test_data[:100].float()
label = dataset.test_labels[:100]
features = images.view(100, 784)
writer.add_embedding(features, metadata=label, label_img=images.unsqueeze(1))
# export scalar data to JSON for external processing
writer.export_scalars_to_json("./all_scalars.json")
writer.close()
运行: python demo.py
会出现runs文件夹,然后在cd到工程目录运行tensorboard --logdir runs
结果:
二,利用 vistom 可视化
参考:https://github.com/facebookresearch/visdom
安装和启动
安装: pip install visdom
启动:python -m visdom.server示例
from visdom import Visdom
#单张
viz.image(
np.random.rand(3, 512, 256),
opts=dict(title=\\\\\'Random!\\\\\', caption=\\\\\'How random.\\\\\'),
)
#多张
viz.images(
np.random.randn(20, 3, 64, 64),
opts=dict(title=\\\\\'Random images\\\\\', caption=\\\\\'How random.\\\\\')
)
from visdom import Visdom
image = np.zeros((100,100))
vis = Visdom()
vis.text("hello world!!!")
vis.image(image)
vis.line(Y = np.column_stack((np.random.randn(10),np.random.randn(10))),
X = np.column_stack((np.arange(10),np.arange(10))),
opts = dict(title = "line", legend=["Test","Test1"]))
三,利用pytorchviz可视化网络结构
参考:https://github.com/szagoruyko/pytorchviz
来源:https://blog.csdn.net/sz793919425/article/details/84305669
标签:Pytorch,可视化
0
投稿
猜你喜欢
解析Python扩展模块的加速方案
2022-12-26 04:53:00
pandas将numpy数组写入到csv的实例
2021-02-07 00:51:00
python中pyplot直方图的绘制方式
2023-11-20 07:58:17
python编程学习使用管道Pipe编写优化代码
2023-08-20 04:08:45
Python API 操作Hadoop hdfs详解
2023-02-24 02:23:26
专家教你安装 MySQL的与MySQL GUI Tools
2012-01-29 17:59:05
SQL Server中导入导出数据的三种方式
2008-11-28 15:53:00
Go语言的Windows下环境配置以及简单的程序结构讲解
2023-08-26 16:04:10
Python的string模块中的Template类字符串模板用法
2023-02-02 10:53:05
Python实现文件及文件夹操作大全
2021-05-22 09:35:21
python打开windows应用程序的实例
2021-08-22 09:49:40
使用Python实现牛顿法求极值
2021-10-14 15:10:21
使用已经得到的keras模型识别自己手写的数字方式
2021-04-03 17:41:11
理解JavaScript作用域链
2010-01-23 11:31:00
python3.4中清屏的处理方法
2023-11-14 04:09:21
Python使用POP3和SMTP协议收发邮件的示例代码
2023-10-03 15:37:28
Python Asyncio 库之同步原语常用函数详解
2021-04-27 03:50:39
Python实现葵花8号卫星数据自动下载实例
2021-09-26 13:40:25
javascript增加干扰数据实现简单加密效果
2011-02-24 11:07:00
python 产生token及token验证的方法
2023-05-19 17:25:13