Pytorch-TensorBoard
简介
TensorBoard：Tensorflow中强大的可视化工具
TensorBoard测试代码
import numpy as np
from torch.utils.tensorboard import SummaryWriter
writer=SummaryWriter(comment='test_tensorboard')
for x in range(100):
writer.add_scalar('y=2x',x*2,x)
writer.add_scalar('y=pow(2,x)',2**x,x)
writer.add_scalars('data/scalar_group',{"sins":x*np.sin(x),
"xcox":x*np.cos(x),
"arctanx":np.arctan(x)},x)
writer.close()
如何读取
在目标文件内命令行内，输入tensorboard --logdir=./runs，其中runs是event_file所在的文件夹
此后在终端内，会出现一个网址一般为:http://localhost:6006/
注意事项
安装时会提示报错，ModuleNotFoundError:No module named ‘past’
通过pip install future解决
SummaryWriter
功能：提供创建event file的高级接口
主要属性：
- log_fir:event file输出文件夹如果不设置，会在当前文件夹下的runs文件夹
- comment:不指定log_dir时，文件夹后缀，如果log_dir为空会生效，给runs文件下的文件夹后缀
- filename_suffix:evebnt file 文件名后缀,给event file文件设置的后缀
方法
1.add_scalar()
功能：记录标量
- tag:图像的标签名，图的唯一标识
- scalar_value:要记录的标量
- global_step:x轴
缺陷：只能记录一条曲线
2.add_scalars()
- main_tag:该图的标签
- tag_scalar_dict:key是变量的tag,value是变量的值
max_epoch = 100
writer = SummaryWriter(comment='test_comment', filename_suffix="test_suffix")
for x in range(max_epoch):
writer.add_scalar('y=2x', x * 2, x)
writer.add_scalar('y=pow_2_x', 2 ** x, x)
writer.add_scalars('data/scalar_group', {"xsinx": x * np.sin(x),
"xcosx": x * np.cos(x)}, x)
writer.close()
3.add_histogram()
功能：统计直方图与多分位数折线图
- tag:图像的标签名，图的唯一标识
- values:要统计的参数
- global_step:y轴
- bins:取直方图bins
writer = SummaryWriter(comment='test_comment', filename_suffix="test_suffix")
for x in range(2):
np.random.seed(x)
data_union = np.arange(100)
data_normal = np.random.normal(size=1000)
writer.add_histogram('distribution union', data_union, x)
writer.add_histogram('distribution normal', data_normal, x)
plt.subplot(121).hist(data_union, label="union")
plt.subplot(122).hist(data_normal, label="normal")
plt.legend()
plt.show()
writer.close()
4.add_image()
功能：记录图像
- tag:图像的标签名，图的唯一标识
- img_tensor:图像数据，注意尺度，如果所有像素点都是(0,1)之间就默认乘以255，如果有像素点大于1就默认所有像素点都是0~255的尺度
- global_step:x轴
- dataformats:数据形式，CHW，HWC，HW
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
# img 1 random
fake_img = torch.randn(3, 512, 512)
writer.add_image("fake_img", fake_img, 1)
time.sleep(1)
# img 2 ones
fake_img = torch.ones(3, 512, 512)
time.sleep(1)
writer.add_image("fake_img", fake_img, 2)
# img 3 1.1
fake_img = torch.ones(3, 512, 512) * 1.1
time.sleep(1)
writer.add_image("fake_img", fake_img, 3)
# img 4 HW
fake_img = torch.rand(512, 512)
writer.add_image("fake_img", fake_img, 4, dataformats="HW")
# img 5 HWC
fake_img = torch.rand(512, 512, 3)
writer.add_image("fake_img", fake_img, 5, dataformats="HWC")
writer.close()
torchvision.utils.make_grid
功能：制作网格图像
可视化MNIST数据集
transform = Compose([transforms.ToTensor()])
datasets=mnist.MNIST(root='./data',train=True,transform=transform,download=True)
datalode=DataLoader(datasets,batch_size=16,num_workers=2)
images,labels=next(iter(datalode))
imagesTogather=tutiles.make_grid(images,nrow=4)
imagesTogather=imagesTogather.transpose(0,2)
import matplotlib.pyplot as plt
plt.imshow(imagesTogather)
plt.show()
可视化卷积核
import torch.nn as nn
from PIL import Image
import torchvision.transforms as transforms
from torch.utils.tensorboard import SummaryWriter
import torchvision.utils as vutils
from tools.common_tools import set_seed
import torchvision.models as models
set_seed(1) # 设置随机种子
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
alexnet = models.alexnet(pretrained=True)
kernel_num = -1
vis_max = 1
for sub_module in alexnet.modules():
if isinstance(sub_module, nn.Conv2d):
kernel_num += 1
if kernel_num > vis_max:
break
kernels = sub_module.weight
c_out, c_int, k_w, k_h = tuple(kernels.shape)
for o_idx in range(c_out):
kernel_idx = kernels[o_idx, :, :, :].unsqueeze(1) # make_grid需要 BCHW，这里拓展C维度
kernel_grid = vutils.make_grid(kernel_idx, normalize=True, scale_each=True, nrow=c_int)
writer.add_image('{}_Convlayer_split_in_channel'.format(kernel_num), kernel_grid, global_step=o_idx)
kernel_all = kernels.view(-1, 3, k_h, k_w) # 3, h, w
kernel_grid = vutils.make_grid(kernel_all, normalize=True, scale_each=True, nrow=8) # c, h, w
writer.add_image('{}_all'.format(kernel_num), kernel_grid, global_step=322)
print("{}_convlayer shape:{}".format(kernel_num, tuple(kernels.shape)))
writer.close()
特征图可视化
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
# 数据
path_img = "./lena.png" # your path to image
normMean = [0.49139968, 0.48215827, 0.44653124]
normStd = [0.24703233, 0.24348505, 0.26158768]
norm_transform = transforms.Normalize(normMean, normStd)
img_transforms = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
norm_transform
])
img_pil = Image.open(path_img).convert('RGB')
if img_transforms is not None:
img_tensor = img_transforms(img_pil)
img_tensor.unsqueeze_(0) # chw --> bchw
# 模型
alexnet = models.alexnet(pretrained=True)
# forward
convlayer1 = alexnet.features[0]
fmap_1 = convlayer1(img_tensor)
# 预处理
fmap_1.transpose_(0, 1) # bchw=(1, 64, 55, 55) --> (64, 1, 55, 55)
fmap_1_grid = vutils.make_grid(fmap_1, normalize=True, scale_each=True, nrow=8)
writer.add_image('feature map in conv1', fmap_1_grid, global_step=322)
writer.close()
5.add_graph()
Pytorch1.2版本存在bug需要求换到1.3版本
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
# 模型
fake_img = torch.randn(1, 3, 32, 32)
lenet = LeNet(classes=2)
writer.add_graph(lenet, fake_img)
writer.close()
torchsummary
此工具包属于第三方工具包，需要pip install安装一下
pip install torchsummary
from torchvision.models import alexnet
Alexnet=alexnet()
from torchsummary import summary
print(summary(Alexnet, (3, 256,256), device="cpu"))
