崇明网站建设,免费ppt模板大全下载的网站,哪家网站游戏做的比较好,贵州网站制作设计公司tensorboard简介
TensorBoard 是一组用于数据可视化的工具。它包含在流行的开源机器学习库 Tensorflow 中.但是也可以独立安装#xff0c;服务Pytorch等其他的框架 可以常常用来观察训练过程中每一阶段如何输出的
安装pip install tensorboard启动tensorboard --logdird…tensorboard简介
TensorBoard 是一组用于数据可视化的工具。它包含在流行的开源机器学习库 Tensorflow 中.但是也可以独立安装服务Pytorch等其他的框架 可以常常用来观察训练过程中每一阶段如何输出的
安装pip install tensorboard启动tensorboard --logdirdirectory_name会默认在6006端口打开也可以自行制定窗口如:tensorboard --logdirlogs --port6007用法
所在类from torch.utils.tensorboard import SummaryWriter介绍class SummaryWriter:Writes entries directly to event files in the log_dir to beconsumed by TensorBoard.The SummaryWriter class provides a high-level API to create an event filein a given directory and add summaries and events to it. The class updates thefile contents asynchronously. This allows a training program to call methodsto add data to the file directly from the training loop, without slowing downtraining.创建对象writer SummaryWriter(logs) # 说明写入哪个文件夹常用方法writer.add_image() # 图像方式
writer.add_scalar() # 坐标方式writer.close() # 使用完之后需要closeadd_scalar() def add_scalar(self,tag,scalar_value,global_stepNone,walltimeNone,new_styleFalse,double_precisionFalse,):Add scalar data to summary.添加标量数据到summary中Args:tag (str): Data identifier 图表标题scalar_value (float or string/blobname): Value to save 数值y轴global_step (int): Global step value to record 训练到多少步x轴walltime (float): Optional override default walltime (time.time())with seconds after epoch of eventnew_style (boolean): Whether to use new style (tensor field) or oldstyle (simple_value field). New style could lead to faster data loading.Examples::from torch.utils.tensorboard import SummaryWriterwriter SummaryWriter()x range(100)for i in x:writer.add_scalar(y2x, i * 2, i)writer.close()Expected result:.. image:: _static/img/tensorboard/add_scalar.png:scale: 50 %注意向writer中写入新事件的同时她也会保留上一个事件这就会导致一些拟合出现问题 解决删除之前的log文件重新生成
add_image()
def add_image(self, tag, img_tensor, global_stepNone, walltimeNone, dataformatsCHW):Add image data to summary.Note that this requires the pillow package.Args:tag (str): Data identifierimg_tensor (torch.Tensor, numpy.ndarray, or string/blobname): Image data 注意数据的类型global_step (int): Global step value to record后面不用管walltime (float): Optional override default walltime (time.time())seconds after epoch of eventdataformats (str): Image data format specification of the formCHW, HWC, HW, WH, etc.Shape:img_tensor: Default is :math:(3, H, W). You can use torchvision.utils.make_grid() toconvert 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 suitable as long ascorresponding dataformats argument is passed, e.g. CHW, HWC, HW.
实践
如在tensorboard中展示图片
from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Imagewriter SummaryWriter(logs)
image_path ./dataset2/train/ants_image/0013035.jpg
img_PIL Image.open(image_path)
img_array np.array(img_PIL)
print(type(img_array))
print(img_array.shape)writer.add_image(test,img_array,1,dataformatsHWC) # 展示读取的图片for i in range(100):writer.add_scalar(y2x, 3*i, i) # 绘图writer.close() writer.add_image中的参数 def add_image(self, tag, img_tensor, global_stepNone, walltimeNone, dataformatsCHW):名称、图形向量ndarray类型第几步是滑动翻页那种的这里相当于设定是第几页每次向后设定时不会清除原来的数据
当前代码效果如图 修改图片后
from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Imagewriter SummaryWriter(logs)
image_path ./dataset2/train/ants_image/5650366_e22b7e1065.jpg
img_PIL Image.open(image_path)
img_array np.array(img_PIL)
print(type(img_array))
print(img_array.shape)# 这里更新说明为第二步
writer.add_image(test,img_array,2,dataformatsHWC)for i in range(100):writer.add_scalar(y2x, 3*i, i)writer.close()拖拉就会发现有两张图
