tensorboard:可視化數據

在anaconda安裝：

pip install tensorboard==2.12.0

最好使用這個版本 不然后面調用會報錯 因為版本過高的原因

然后還碰到了安裝的時候 安裝到C盤去了 但是我用的虛擬環境是在E盤：此時去C盤把那些新安裝的復制過來就好了 附錄我C盤的路徑：C:\Users\asus\AppData\Roaming\Python\Python38\Scripts

（搜索了一下有大佬說可能是python版本的問題 以后pip/conda install的時候指定一下python版本 可以先在虛擬環境中python --version查看一下）

transforms:數據增強（數據預處理）

transforms是個工具箱 里面有很多工具 可以處理圖片得到一個結果

tool = transforms.totensor()

result = tool(input)

為什么非要轉化成tensor型？因為它里面有很多神經網絡深度學習的參數 想要訓練就需要tensor型

常見的transforms工具(按住ctrl可以進入源碼)

1. ToTensor()

   code：

   from PIL import Image
   from torch.utils.tensorboard import SummaryWriter
   from torchvision import transformswriter = SummaryWriter('../logs')
   #tensorboard --logdir=../logs
   img = Image.open('../images/1.jpg')
   print(img)# use TOTensor()
   trans_tensor = transforms.ToTensor()
   img_tensor = trans_tensor(img)
   writer.add_image('totensor',img_tensor,dataformats='CHW')writer.close()
   

   logs:

   

2. Normalize() 標準化

   設置Normalize([0.5,0.5,0.5],[0.5,0.5,0.5]) （這樣設置可以實現歸一化）

   input[channel] = (input[channel] - mean[channel]) / std[channel]

   =(input - 0.5) / 0.5

   =2 * input - 1

   input [0,1]

   result [-1,1]

   code:(在writer.close()之前加上)

   # use Normalize()
   print(img_tensor[0][0][0])
   trans_norm = transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
   #trans_norm = transforms.Normalize([1,2,3],[3,2,1])
   img_norm = trans_norm(img_tensor)
   print(img_norm[0][0][0])
   writer.add_image('normalize',img_norm)
   #writer.add_image('normalize',img_norm,1)
   

   logs:

   

   可以換幾個數據試一下：（冬天寒冷小蘇 變成夏天紅溫小蘇了）

   

3. Resize()

   改變圖片大小

   code：

   #use Resize()
   print(img.size)
   trans_resize = transforms.Resize((512,512))
   img_resize = trans_resize(img)
   img_resize = trans_totensor(img_resize)
   print(img_resize)
   writer.add_image('resize',img_resize,0)
   

   好吧：是拉伸小餅

   

4. Compose()

   串聯多個圖片變換的操作

   code:

   #use Compose() - Resize() - 2
   trans_resize_2 = transforms.Resize(512)
   trans_compose = transforms.Compose([trans_resize_2,trans_totensor])
   img_resize_2 = trans_compose(img)
   writer.add_image('resize',img_resize_2,1)
   

   

5. RandomCrop()

   隨機裁剪

   code：

   #use RandomCrop()
   trans_random = transforms.RandomCrop(512)
   trans_compose_2 = transforms.Compose([trans_random,trans_totensor])
   #隨機裁剪十次
   for i in range(10):img_crop = trans_compose_2(img)writer.add_image('random_crop',img_crop,i)
   

   

   

   還可以根據寬和高裁剪的

   code：

   trans_random = transforms.RandomCrop((500,1000))
   trans_compose_3 = transforms.Compose([trans_random,trans_totensor])
   for i in range(10):img_crop = trans_compose_3(img)writer.add_image('random_crophw',img_crop,i)
   

   

6. 以上完整代碼

   先展示目錄結構：

   

   code：

   from PIL import Image
   from torch.utils.tensorboard import SummaryWriter
   from torchvision import transforms
   import cv2
   import numpy as npwriter = SummaryWriter('../logs')
   #tensorboard --logdir=../logs
   img = Image.open('../images/1.jpg')
   print(img)# use TOTensor()
   trans_totensor = transforms.ToTensor()
   img_tensor = trans_totensor(img)
   writer.add_image('totensor',img_tensor,dataformats='CHW')# use Normalize()
   print(img_tensor[0][0][0])
   trans_norm = transforms.Normalize([1,2,3],[3,2,1])
   img_norm = trans_norm(img_tensor)
   print(img_norm[0][0][0])
   writer.add_image('normalize',img_norm,1)#use Resize()
   print(img.size)
   trans_resize = transforms.Resize((512,512))
   img_resize = trans_resize(img)
   img_resize = trans_totensor(img_resize)
   print(img_resize)
   writer.add_image('resize',img_resize,0)#use Compose() - Resize() - 2
   trans_resize_2 = transforms.Resize(512)
   trans_compose = transforms.Compose([trans_resize_2,trans_totensor])
   img_resize_2 = trans_compose(img)
   writer.add_image('resize',img_resize_2,1)#use RandomCrop()
   trans_random = transforms.RandomCrop(512)
   trans_compose_2 = transforms.Compose([trans_random,trans_totensor])
   for i in range(10):img_crop = trans_compose_2(img)writer.add_image('random_crop',img_crop,i)trans_random = transforms.RandomCrop((500,1000))
   trans_compose_3 = transforms.Compose([trans_random,trans_totensor])
   for i in range(10):img_crop = trans_compose_3(img)writer.add_image('random_crophw',img_crop,i)writer.close()