pytorch 使用visdom進行視覺化

相比tensorbordx, visdom重新整理更快，介面體驗也良好，首先是visdom的安裝，與普通的python庫一樣，直接pip install visdom即可

成功安裝後，在控制台下輸入python -m visdom.server

複製http://localhost:8097，輸入瀏覽器即可開啟visdom視覺化視窗

呼叫visdom主要需要如下語句：

from visdom import visdom

# your code
vis = visdom()
# vis = visdom(env = 'my window') 可接收env引數，用於標識視窗控制代碼
# your data need to be drawn

import numpy as np

import matplotlib.pyplot as plt
import torch.optim as optim
from visdom import visdom
import torch
import torch.nn as nn
num_step =
50input_size =
1output_size =
1hidden_size =
16lr =
0.01
device =
'cpu'
class
rnnnet
(nn.module)
:def
__init__
(self)
:super
(rnnnet, self)
.__init__(
) self.rnn = nn.rnn(
input_size=input_size,
hidden_size=hidden_size,
num_layers=1,
batch_first=
true
) self.linear = nn.linear(hidden_size, output_size)
defforward
(self, x, hidden)
: out, hidden = self.rnn(x, hidden)
out = out.view(-1
, hidden_size)
out = self.linear(out)
out = out.unsqueeze(dim=0)
return out, hidden
if __name__ ==
'__main__'
: rnnnet = rnnnet(
).to(device)
loss_func = nn.mseloss(
) optimizer = optim.adam(rnnnet.parameters(
), lr=lr)
hidden = torch.zeros(1,
1, hidden_size)
global_step =
0 vis = visdom(
)# win 表徵該env下的視窗控制代碼，乙個win代表乙個視窗，視窗標題由title決定
vis.line([0
.],[
0.], win=
'train_loss'
, opts=
dict
(title=
'train loss'))
for epoch in
range
(10000):
start = np.random.randint(
3, size=1)
[0] time_steps = np.linspace(start, start+
10, num_step)
data = np.sin(time_steps)
data = data.reshape(num_step,1)
x = torch.tensor(data[:-
1]).
float()
.view(
1, num_step -1,
1).to(device)
y = torch.tensor(data[1:
]).float()
.view(
1, num_step -1,
1).to(device)
output, hidden = rnnnet(x, hidden)
hidden = hidden.detach(
) loss = loss_func(output, y)
optimizer.zero_grad(
) loss.backward(
) optimizer.step(
) global_step +=
1 vis.line(
[loss.item()]
,[global_step]
, win=
'train_loss'
, update=
)if epoch %
100==0:
print
("iteration: {} loss: {}"
.format
(epoch, loss.item())
)

env標識的即上面的main，改變引數後可在下拉框中選擇目標視窗

PyTorch 使用Visdom訓練資料視覺化

安裝與啟動 安裝 pip install visdom 終端啟動 python m visdom.server 開啟瀏覽器，位址列輸入 上面鏈結也給出了具體的操作方法 編寫乙個最簡單的繪製正弦曲線程式 import numpy as np import visdom def drawonlne 在這...

使用visdom視覺化pytorch訓練過程

1 安裝 pip install visdom 或者conda install c conda forge visdom 2 啟動服務 python m visdom.server 瀏覽器輸入http localhost 8097檢視 3 使用 參考 from visdom import visdo...

在PyTorch中使用Visdom視覺化工具

在pytorch中使用visdom視覺化工具 非常詳細 參考鏈結二 1.安裝 pip install visdom conda install visdom 2.linux 伺服器端 啟動 模型訓練前 預設使用埠 8097 to view training results and loss plot...