OxfordIIITPet in PyTorch

Buy Me a Coffee☕

*My post explains Oxford-IIIT Pet.

OxfordIIITPet() can use Oxford-IIIT Pet dataset as shown below:

*Memos:

• The 1st argument is root(Required-Type:str or pathlib.Path). *An absolute or relative path is possible.
• The 2nd argument is split(Optional-Default:"train"-Type:str). *"trainval"(3,680 images) or "test"(3,669 images) can be set to it.
• The 3rd argument is target_types(Optional-Default:"attr"-Type:str or list of str): *Memos:
  • "category", "binary-category" and/or "segmentation" can be set to it: *Memos:
  • "category" is for the label from 37 categories(classes).
  • "binary-category" is for the label of cat(0) or dog(1).
  • "segmentation" is for a segmentation trimap image.
  • An empty tuple or list can also be set to it.
  • The multiple same values can be set to it.
  • If the order of values is different, the order of their elements is also different.
• The 4th argument is transform(Optional-Default:None-Type:callable).
• The 5th argument is target_transform(Optional-Default:None-Type:callable).
• The 6th argument is download(Optional-Default:False-Type:bool): *Memos:
  • If it's True, the dataset is downloaded from the internet and extracted(unzipped) to root.
  • If it's True and the dataset is already downloaded, it's extracted.
  • If it's True and the dataset is already downloaded and extracted, nothing happens.
  • It should be False if the dataset is already downloaded and extracted because it's faster.
  • You can manually download and extract the dataset(images.tar.gz and annotations.tar.gz) from here to data/oxford-iiit-pet/.
• About the label from the categories(classes) for the train image indices, Abyssinian(0) is 0~49, American Bulldog(1) is 50~99, American Pit Bull Terrier(2) is 100~149, Basset Hound(3) is 150~199, Beagle(4) is 200~249, Bengal(5) is 250~299, Birman(6) is 300~349, Bombay(7) is 350~398, Boxer(8) is 399~448, British Shorthair(9) is 449~498, etc.
• About the label from the categories(classes) for the test image indices, Abyssinian(0) is 0~97, American Bulldog(1) is 98~197, American Pit Bull Terrier(2) is 198~297, Basset Hound(3) is 298~397, Beagle(4) is 398~497, Bengal(5) is 498~597, Birman(6) is 598~697, Bombay(7) is 698~785, Boxer(8) is 786~884, British Shorthair(9) is 885~984, etc.

from torchvision.datasets import OxfordIIITPet

trainval_cate_data = OxfordIIITPet(
    root="data"
)

trainval_cate_data = OxfordIIITPet(
    root="data",
    split="trainval",
    target_types="category",
    transform=None,
    target_transform=None,
    download=False
)

trainval_bincate_data = OxfordIIITPet(
    root="data",
    split="trainval",
    target_types="binary-category"
)

test_seg_data = OxfordIIITPet(
    root="data",
    split="test",
    target_types="segmentation"
)

test_empty_data = OxfordIIITPet(
    root="data",
    split="test",
    target_types=[]
)

test_all_data = OxfordIIITPet(
    root="data",
    split="test",
    target_types=["category", "binary-category", "segmentation"]
)

len(trainval_cate_data), len(trainval_bincate_data)
# (3680, 3680)

len(test_seg_data), len(test_empty_data), len(test_all_data)
# (3669, 3669, 3669)

trainval_cate_data
# Dataset OxfordIIITPet
#     Number of datapoints: 3680
#     Root location: data

trainval_cate_data.root
# 'data'

trainval_cate_data._split
# 'trainval'

trainval_cate_data._target_types
# ['category']

print(trainval_cate_data.transform)
# None

print(trainval_cate_data.target_transform)
# None

trainval_cate_data._download
# <bound method OxfordIIITPet._download of Dataset OxfordIIITPet
#     Number of datapoints: 3680
#     Root location: data>

len(trainval_cate_data.classes), trainval_cate_data.classes
# (37,
#  ['Abyssinian', 'American Bulldog', 'American Pit Bull Terrier',
#   'Basset Hound', 'Beagle', 'Bengal', 'Birman', 'Bombay', 'Boxer',
#   'British Shorthair', ..., 'Wheaten Terrier', 'Yorkshire Terrier'])

trainval_cate_data[0]
# (<PIL.Image.Image image mode=RGB size=394x500>, 0)

trainval_cate_data[1]
# (<PIL.Image.Image image mode=RGB size=450x313>, 0)

trainval_cate_data[2]
# (<PIL.Image.Image image mode=RGB size=500x465>, 0)

trainval_bincate_data[0]
# (<PIL.Image.Image image mode=RGB size=394x500>, 0)

trainval_bincate_data[1]
# (<PIL.Image.Image image mode=RGB size=450x313>, 0)

trainval_bincate_data[2]
# (<PIL.Image.Image image mode=RGB size=500x465>, 0)

test_seg_data[0]
# (<PIL.Image.Image image mode=RGB size=300x225>,
#  <PIL.PngImagePlugin.PngImageFile image mode=L size=300x225>)

test_seg_data[1]
# (<PIL.Image.Image image mode=RGB size=300x225>,
#  <PIL.PngImagePlugin.PngImageFile image mode=L size=300x225>)

test_seg_data[2]
# (<PIL.Image.Image image mode=RGB size=229x300>,
#  <PIL.PngImagePlugin.PngImageFile image mode=L size=229x300>)

test_empty_data[0]
# (<PIL.Image.Image image mode=RGB size=300x225>, None)

test_empty_data[1]
# (<PIL.Image.Image image mode=RGB size=300x225>, None)

test_empty_data[2]
# (<PIL.Image.Image image mode=RGB size=229x300>, None)

test_all_data[0]
# (<PIL.Image.Image image mode=RGB size=300x225>,
#  (0, 0, <PIL.PngImagePlugin.PngImageFile image mode=L size=300x225>))

test_all_data[1]
# (<PIL.Image.Image image mode=RGB size=300x225>,
#  (0, 0, <PIL.PngImagePlugin.PngImageFile image mode=L size=300x225>))

test_all_data[2]
# (<PIL.Image.Image image mode=RGB size=229x300>,
#  (0, 0, <PIL.PngImagePlugin.PngImageFile image mode=L size=229x300>))

import matplotlib.pyplot as plt

def show_images(data, ims, main_title=None):
    if len(data._target_types) == 0:      
        plt.figure(figsize=(12, 6))
        plt.suptitle(t=main_title, y=1.0, fontsize=14)
        for i, j in enumerate(ims, start=1):
            plt.subplot(2, 5, i)
            im, _ = data[j]
            plt.imshow(X=im)
    elif len(data._target_types) == 1:
        if data._target_types[0] == "category":
            plt.figure(figsize=(12, 6))
            plt.suptitle(t=main_title, y=1.0, fontsize=14)
            for i, j in enumerate(ims, start=1):
                plt.subplot(2, 5, i)
                im, cate = data[j]
                plt.title(label=cate)
                plt.imshow(X=im)
        elif data._target_types[0] == "binary-category":
            plt.figure(figsize=(12, 6))
            plt.suptitle(t=main_title, y=1.0, fontsize=14)
            for i, j in enumerate(ims, start=1):
                plt.subplot(2, 5, i)
                im, bincate = data[j]
                plt.title(label=bincate)
                plt.imshow(X=im)
        elif data._target_types[0] == "segmentation":
            plt.figure(figsize=(12, 12))
            plt.suptitle(t=main_title, y=1.0, fontsize=14)
            for i, j in enumerate(ims, start=1):
                im, seg = data[j]
                if 1 <= i and i <= 5:
                    plt.subplot(4, 5, i)
                    plt.imshow(X=im)
                    plt.subplot(4, 5, i+5)
                    plt.imshow(X=seg)
                if 6 <= i and i <= 10:
                    plt.subplot(4, 5, i+5)
                    plt.imshow(X=im)
                    plt.subplot(4, 5, i+10)
                    plt.imshow(X=seg)
    elif len(data._target_types) == 3:
        plt.figure(figsize=(12, 12))
        plt.suptitle(t=main_title, y=1.0, fontsize=14)
        for i, j in enumerate(ims, start=1):
            im, (cate, bincate, seg) = data[j]
            if 1 <= i and i <= 5:
                plt.subplot(4, 5, i)
                plt.title(label=f"{cate}, {bincate}")
                plt.imshow(X=im)
                plt.subplot(4, 5, i+5)
                plt.imshow(X=seg)
            if 6 <= i and i <= 10:
                plt.subplot(4, 5, i+5)
                plt.title(label=f"{cate}, {bincate}")
                plt.imshow(X=im)
                plt.subplot(4, 5, i+10)
                plt.imshow(X=seg)
    plt.tight_layout(h_pad=3.0)
    plt.show()

train_ims = (0, 1, 2, 50, 100, 150, 200, 250, 300, 350)
test_ims = (0, 1, 2, 98, 198, 298, 398, 498, 598, 698)

show_images(data=trainval_cate_data, ims=train_ims,
            main_title="trainval_cate_data")
show_images(data=trainval_bincate_data, ims=train_ims, 
            main_title="trainval_bincate_data")
show_images(data=test_seg_data, ims=test_ims,
            main_title="test_seg_data")
show_images(data=test_empty_data, ims=test_ims,
            main_title="test_empty_data")
show_images(data=test_all_data, ims=test_ims,
            main_title="test_all_data")

The above is the detailed content of OxfordIIITPet in PyTorch. For more information, please follow other related articles on the PHP Chinese website!