Dev.to

AugMix in PyTorch (1)

Buy Me a Coffee☕ Memos: My post explains RandAugment() about num_ops and fill argument. My post explains AutoAugment(). My post explains TrivialAugmentWide(). My post explains OxfordIIITPet(). AugMix() can randomly do AugMix to an image as shown below: Memos: The 1st argument for initialization is severity(Optional-Default:3-Type:int). *It must be 1

Mar 8, 2025 - 01:05

Buy Me a Coffee☕

*Memos:

My post explains RandAugment() about num_ops and fill argument.
My post explains AutoAugment().
My post explains TrivialAugmentWide().
My post explains OxfordIIITPet().

AugMix() can randomly do AugMix to an image as shown below:

*Memos:

The 1st argument for initialization is severity(Optional-Default:3-Type:int). *It must be 1 <= x <= 10.
The 2nd argument for initialization is mixture_width(Optional-Default:3-Type:int).
The 3rd argument for initialization is chain_depth(Optional-Default:-1-Type:int). *If it's x <= 0, it's randomly taken from the interval [1, 3].
The 4th argument for initialization is alpha(Optional-Default:1.0-Type:float). *It must be 1 <= x.
The 5th argument for initialization is all_ops(Optional-Default:True-Type:bool). *It must be 1 <= x.
The 6th argument for initialization is interpolation(Optional-Default:InterpolationMode.NEAREST-Type:InterpolationMode). *If the input is a tensor, only InterpolationMode.NEAREST and InterpolationMode.BILINEAR can be set to it.
The 7th argument for initialization is fill(Optional-Default:0-Type:int, float or tuple/list(int or float)): *Memos:
- It can change the background of an image. *The background can be seen when doing AugMix to an image.
- A tuple/list must be the 1D with 1 or 3 elements.
- If all values are x <= 0, it's black.
- If all values are 255 <= x, it's white.
The 1st argument is img(Required-Type:PIL Image or tensor(int)): *Memos:
- A tensor must be 2D or 3D.
- Don't use img=.
v2 is recommended to use according to V1 or V2? Which one should I use?.

from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import AugMix
from torchvision.transforms.functional import InterpolationMode

am = AugMix()
am = AugMix(severity=3, mixture_width=3, chain_depth=-1, alpha=1.0, 
            all_ops=True, interpolation=InterpolationMode.BILINEAR,
            fill=None)
am
# AugMix(interpolation=InterpolationMode.BILINEAR, severity=3,
#        mixture_width=3, chain_depth=-1, alpha=1.0, all_ops=True)

am.severity
# 3

am.mixture_width
# 3

am.chain_depth
# -1

am.alpha
# 1.0

am.all_ops
# True

am.interpolation
# 

print(am.fill)
# None

origin_data = OxfordIIITPet(
    root="data",
    transform=None
)

default_data = OxfordIIITPet(
    root="data",
    transform=AugMix()
)

aoFalse_data = OxfordIIITPet( # `ao` is all_ops.
    root="data",
    transform=AugMix(all_ops=False)
    # transform=AugMix(severity=3, mixture_width=3, chain_depth=-1, 
    #                  alpha=1.0, all_ops=True,
    #                  interpolation=InterpolationMode.BILINEAR,
    #                  fill=None)
)

s10cd25fgray_data = OxfordIIITPet( # `s` is severity and `cd` is chain_depth.
    root="data",                   # `f` is fill.
    transform=AugMix(severity=10, chain_depth=25, fill=150)
)

s10cd25fpurple_data = OxfordIIITPet(
    root="data",
    transform=AugMix(severity=10, chain_depth=25, fill=[160, 32, 240])
)

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.xticks(ticks=[])
        plt.yticks(ticks=[])
    plt.tight_layout()
    plt.show()

show_images1(data=origin_data, main_title="origin_data")
print()
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
show_images1(data=default_data, main_title="default_data")
print()
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
show_images1(data=aoFalse_data, main_title="aoFalse_data")
print()
show_images1(data=s10cd25fgray_data, main_title="s10cd25fgray_data")
show_images1(data=s10cd25fpurple_data, main_title="s10cd25fpurple_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, s=3, mw=3, cd=-1, a=1.0,
                 ao=True, ip=InterpolationMode.BILINEAR, f=None):
    plt.figure(figsize=[10, 5])
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    if main_title != "origin_data":
        for i, (im, _) in zip(range(1, 6), data):
            plt.subplot(1, 5, i)
            am = AugMix(severity=s, mixture_width=mw, chain_depth=cd,
                        alpha=a, all_ops=ao, interpolation=ip, fill=f)
            plt.imshow(X=am(im))
            plt.xticks(ticks=[])
            plt.yticks(ticks=[])
    else:
        for i, (im, _) in zip(range(1, 6), data):
            plt.subplot(1, 5, i)
            plt.imshow(X=im)
            plt.xticks(ticks=[])
            plt.yticks(ticks=[])
    plt.tight_layout()
    plt.show()

show_images2(data=origin_data, main_title="origin_data")
print()
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
show_images2(data=origin_data, main_title="default_data")
print()
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
show_images2(data=origin_data, main_title="aoFalse_data", ao=False)
print()
show_images2(data=origin_data, main_title="s10cd25fgray_data", s=10, cd=25,
             f=150)
show_images2(data=origin_data, main_title="s10cd25fpurple_data", s=10, 
             cd=25, f=[160, 32, 240])