pytorch中的随机溶剂（5）

有志者，事竟成！如果你在学习文章，那么本文《pytorch中的随机溶剂（5）》，就很适合你！文章讲解的知识点主要包括，若是你对本文感兴趣，或者是想搞懂其中某个知识点，就请你继续往下看吧~

给我买咖啡☕

*备忘录：

• 我的帖子说明了关于大小参数的randomresizedcrop（）。
我的帖子解释了有关比例参数的randomresizedcrop（）。
• 我的帖子解释了关于比率参数的randomresizedcrop（）。
>
• 我的帖子解释了随机rastizedcrop（）关于尺寸参数，比例= [0，0]和比率= [1，1]。
我的帖子解释了与比例参数有关的随机rastresizedcrop（），scale = [0，0]。
• 我的帖子解释了牛津iiitpet（）。
randomresizedcrop（）可以裁剪图像的随机部分，然后将其调整为给定尺寸，如下所示：

• from torchvision.datasets import OxfordIIITPet
  from torchvision.transforms.v2 import RandomResizedCrop
  from torchvision.transforms.functional import InterpolationMode
  
  origin_data = OxfordIIITPet(
      root="data",
      transform=None
  )
  
  s1000sc0_0r1_1origin_data = OxfordIIITPet( # `s` is size and `sc` is scale.
      root="data",                           # `r` is ratio.
      transform=RandomResizedCrop(size=1000, scale=[0, 0], ratio=[1, 1])
  )
  
  s1000sc0_1r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0, 1], ratio=[1, 1])
  )
  
  s1000sc0_05r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0, 0.5], ratio=[1, 1])
  )
  
  s1000sc05_1r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.5, 1], ratio=[1, 1])
  )
  
  s1000sc0001_0001r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.001, 0.001],
                                  ratio=[1, 1])
  )
  
  s1000sc001_001r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.01, 0.01], ratio=[1, 1])
  )
  
  s1000sc01_01r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.1, 0.1], ratio=[1, 1])
  )
  
  s1000sc02_02r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.2, 0.2], ratio=[1, 1])
  )
  
  s1000sc03_03r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.3, 0.3], ratio=[1, 1])
  )
  
  s1000sc04_04r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.4, 0.4], ratio=[1, 1])
  )
  
  s1000sc05_05r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.5, 0.5], ratio=[1, 1])
  )
  
  s1000sc06_06r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.6, 0.6], ratio=[1, 1])
  )
  
  s1000sc07_07r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.7, 0.7], ratio=[1, 1])
  )
  
  s1000sc08_08r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.8, 0.8], ratio=[1, 1])
  )
  
  s1000sc09_09r1_1_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[0.9, 0.9], ratio=[1, 1])
  )
  
  s1000sc1_1r1_1origin_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[1, 1], ratio=[1, 1])
  )
  
  s1000sc10_10r1_1origin_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[10, 10], ratio=[1, 1])
  )
  
  s1000sc100_100r1_1origin_data = OxfordIIITPet(
      root="data",
      transform=RandomResizedCrop(size=1000, scale=[100, 100], ratio=[1, 1])
  )
  
  import matplotlib.pyplot as plt
  
  def show_images1(data, main_title=None):
      plt.figure(figsize=[10, 5])
      plt.suptitle(t=main_title, y=0.8, fontsize=14)
      for i, (im, _) in zip(range(1, 6), data):
          plt.subplot(1, 5, i)
          plt.imshow(X=im)
      plt.tight_layout()
      plt.show()
  
  show_images1(data=origin_data, main_title="origin_data")
  print()
  show_images1(data=s1000sc0_0r1_1origin_data,
               main_title="s1000sc0_0r1_1origin_data")
  show_images1(data=s1000sc0_1r1_1_data, main_title="s1000sc0_1r1_1_data")
  show_images1(data=s1000sc0_05r1_1_data, main_title="s1000sc0_05r1_1_data")
  show_images1(data=s1000sc05_1r1_1_data, main_title="s1000sc05_1r1_1_data")
  print()
  show_images1(data=s1000sc0_0r1_1origin_data,
               main_title="s1000sc0_0r1_1origin_data")
  show_images1(data=s1000sc0001_0001r1_1_data, 
               main_title="s1000sc0001_0001r1_1_data")
  show_images1(data=s1000sc001_001r1_1_data, 
               main_title="s1000sc001_001r1_1_data")
  show_images1(data=s1000sc01_01r1_1_data, main_title="s1000sc01_01r1_1_data")
  show_images1(data=s1000sc02_02r1_1_data, main_title="s1000sc02_02r1_1_data")
  show_images1(data=s1000sc03_03r1_1_data, main_title="s1000sc03_03r1_1_data")
  show_images1(data=s1000sc04_04r1_1_data, main_title="s1000sc04_04r1_1_data")
  show_images1(data=s1000sc05_05r1_1_data, main_title="s1000sc05_05r1_1_data")
  show_images1(data=s1000sc06_06r1_1_data, main_title="s1000sc06_06r1_1_data")
  show_images1(data=s1000sc07_07r1_1_data, main_title="s1000sc07_07r1_1_data")
  show_images1(data=s1000sc08_08r1_1_data, main_title="s1000sc08_08r1_1_data")
  show_images1(data=s1000sc09_09r1_1_data, main_title="s1000sc09_09r1_1_data")
  show_images1(data=s1000sc1_1r1_1origin_data, 
               main_title="s1000sc1_1r1_1origin_data")
  show_images1(data=s1000sc10_10r1_1origin_data,
               main_title="s1000sc10_10r1_1origin_data")
  show_images1(data=s1000sc100_100r1_1origin_data,
               main_title="s1000sc100_100r1_1origin_data")
  
  # ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓ 
  def show_images2(data, main_title=None, s=None, sc=(0.08, 1.0),
                   r=(0.75, 1.3333333333333333),
                   ip=InterpolationMode.BILINEAR, a=True):
      plt.figure(figsize=[10, 5])
      plt.suptitle(t=main_title, y=0.8, fontsize=14)
      for i, (im, _) in zip(range(1, 6), data):
          plt.subplot(1, 5, i)
          if s:
              rrc = RandomResizedCrop(size=s, scale=sc, # Here
                                      ratio=r, interpolation=ip,
                                      antialias=a)
              plt.imshow(X=rrc(im)) # Here
          else:
              plt.imshow(X=im)
      plt.tight_layout()
      plt.show()
  
  show_images2(data=origin_data, main_title="origin_data")
  print()
  show_images2(data=origin_data, main_title="s1000sc0_0r1_1origin_data",
               s=1000, sc=[0, 0], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc0_1r1_1_data", s=1000, 
               sc=[0, 1], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc0_05r1_1_data", s=1000,
               sc=[0, 0.5], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc05_1r1_1_data", s=1000,
               sc=[0.5, 1], r=[1, 1])
  print()
  show_images2(data=origin_data, main_title="s1000sc0_0r1_1origin_data", 
               s=1000, sc=[0, 0], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc0001_0001r1_1_data", 
               s=1000, sc=[0.001, 0.001], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc001_001r1_1_data", 
               s=1000, sc=[0.01, 0.01], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc01_01r1_1_data", 
               s=1000, sc=[0.1, 0.1], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc02_02r1_1_data", 
               s=1000, sc=[0.2, 0.2], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc03_03r1_1_data", 
               s=1000, sc=[0.3, 0.3], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc04_04r1_1_data", 
               s=1000, sc=[0.4, 0.4], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc05_05r1_1_data", 
               s=1000, sc=[0.5, 0.5], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc06_06r1_1_data", 
               s=1000, sc=[0.6, 0.6], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc07_07r1_1_data", 
               s=1000, sc=[0.7, 0.7], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc08_08r1_1_data", 
               s=1000, sc=[0.8, 0.8], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc09_09r1_1_data", 
               s=1000, sc=[0.9, 0.9], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc1_1r1_1origin_data", 
               s=1000, sc=[1, 1], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc10_10r1_1origin_data",
               s=1000, sc=[10, 10], r=[1, 1])
  show_images2(data=origin_data, main_title="s1000sc100_100r1_1origin_data",
               s=1000, sc=[100, 100], r=[1, 1])
  

终于介绍完啦！小伙伴们，这篇关于《pytorch中的随机溶剂（5）》的介绍应该让你收获多多了吧！欢迎大家收藏或分享给更多需要学习的朋友吧~golang学习网公众号也会发布文章相关知识，快来关注吧！