Caltech101 in PyTorch

#python #pytorch #caltech101 #dataset

Buy Me a Coffee☕

*My post explains Caltech 101.

Caltech101() can use Caltech 101 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 target_type(Optional-Default:"category"-Type:str or tuple or list of str): *Memos:
- "category" and/or "annotation" can be set to it. *The order doesn't matter.
- The 8.677 images with the labels from 101 categories(classes) and/or with annotations are returned.
The 3rd argument is transform(Optional-Default:None-Type:callable).
The 4th argument is target_transform(Optional-Default:None-Type:callable).
The 5th 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.
- gdown is required to download the dataset.
- You can manually download and extract the dataset(101_ObjectCategories.tar.gz and Annotations.tar) from here to data/caltech101/.
About the categories(labels) of the image indices, Faces(0) is 0~434, Faces_easy(1) is 435~869, Leopards(2) is 870~1069, Motorbikes(3) is 1070~1867, accordion(4) is 1868~1922, airplanes(5) is 1923~2722, anchor(6) is 2723~2764, ant(7) is 2765~2806, barrel(8) is 2807~2853, bass(9) is 2854~2907, etc.

from torchvision.datasets import Caltech101

category_data = Caltech101(
    root="data"
)

category_data = Caltech101(
    root="data",
    target_type="category",
    transform=None,
    target_transform=None,
    download=False
)

annotation_data = Caltech101(
    root="data",
    target_type="annotation"
)

all_data = Caltech101(
    root="data",
    target_type=["category", "annotation"]
)

len(category_data), len(annotation_data), len(all_data)
# (8677, 8677, 8677)

category_data
# Dataset Caltech101
#     Number of datapoints: 8677
#     Root location: data\caltech101
#     Target type: ['category']

category_data.root
# 'data/caltech101'

category_data.target_type
# ['category']

print(category_data.transform)
# None

print(category_data.target_transform)
# None

category_data.download
# <bound method Caltech101.download of Dataset Caltech101
#     Number of datapoints: 8677
#     Root location: data\caltech101
#     Target type: ['category']>

len(category_data.categories)
# 101

category_data.categories
# ['Faces', 'Faces_easy', 'Leopards', 'Motorbikes', 'accordion', 
#  'airplanes', 'anchor', 'ant', 'barrel', 'bass', 'beaver',
#  'binocular', 'bonsai', 'brain', 'brontosaurus', 'buddha',
#  'butterfly', 'camera', 'cannon', 'car_side', 'ceiling_fan',
#  'cellphone', 'chair', 'chandelier', 'cougar_body', 'cougar_face', ...]

len(category_data.annotation_categories)
# 101

category_data.annotation_categories
# ['Faces_2', 'Faces_3', 'Leopards', 'Motorbikes_16', 'accordion',
#  'Airplanes_Side_2', 'anchor', 'ant', 'barrel', 'bass', 'beaver',
#  'binocular', 'bonsai', 'brain', 'brontosaurus', 'buddha',
#  'butterfly', 'camera', 'cannon', 'car_side', 'ceiling_fan',
#  'cellphone', 'chair', 'chandelier', 'cougar_body', 'cougar_face', ...]

category_data[0]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=510x337>, 0)

category_data[1]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=519x343>, 0)

category_data[2]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=492x325>, 0)

category_data[435]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=290x334>, 1)

category_data[870]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=192x128>, 2)

annotation_data[0]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=510x337>,
#  array([[10.00958466, 8.18210863, 8.18210863, 10.92332268, ...],
#         [132.30670927, 120.42811502, 103.52396166, 90.73162939, ...]]))

annotation_data[1]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=519x343>,
#  array([[15.19298246, 13.71929825, 15.19298246, 19.61403509, ...],
#         [121.5877193, 103.90350877, 80.81578947, 64.11403509, ...]]))

annotation_data[2]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=492x325>,
#  array([[10.40789474, 7.17807018, 5.79385965, 9.02368421, ...],
#         [131.30789474, 120.69561404, 102.23947368, 86.09035088, ...]]))

annotation_data[435]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=290x334>,
#  array([[64.52631579, 95.31578947, 123.26315789, 149.31578947, ...],
#         [15.42105263, 8.31578947, 10.21052632, 28.21052632, ...]]))

annotation_data[870]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=192x128>,
#  array([[2.96536524, 7.55604534, 19.45780856, 33.73992443, ...],
#         [23.63413098, 32.13539043, 33.83564232, 8.84193955, ...]]))

all_data[0]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=510x337>,
#  (0, array([[10.00958466, 8.18210863, 8.18210863, 10.92332268, ...],
#             [132.30670927, 120.42811502, 103.52396166, 90.73162939, ...]]))

all_data[1]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=519x343>,
#  (0, array([[15.19298246, 13.71929825, 15.19298246, 19.61403509, ...],
#             [121.5877193, 103.90350877, 80.81578947, 64.11403509, ...]]))

all_data[2]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=492x325>,
#  (0, array([[10.40789474, 7.17807018, 5.79385965, 9.02368421, ...],
#             [131.30789474, 120.69561404, 102.23947368, 86.09035088, ...]]))

all_data[3]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=538x355>,
#  (0, array([[19.54035088, 18.57894737, 26.27017544, 38.2877193, ...],
#             [131.49122807, 100.24561404, 74.2877193, 49.29122807, ...]]))

all_data[4]
# (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=528x349>,
#  (0, array([[11.87982456, 11.87982456, 13.86578947, 15.35526316, ...],
#             [128.34649123, 105.50789474, 91.60614035, 76.71140351, ...]]))

import matplotlib.pyplot as plt

def show_images(data, main_title=None):
    plt.figure(figsize=(10, 5))
    plt.suptitle(t=main_title, y=1.0, fontsize=14)
    ims = (0, 1, 2, 435, 870, 1070, 1868, 1923, 2723, 2765)
    for i, j in enumerate(ims, start=1):
        plt.subplot(2, 5, i)
        if len(data.target_type) == 1:
            if data.target_type[0] == "category":
                im, lab = data[j]
                plt.title(label=lab)
            elif data.target_type[0] == "annotation":
                im, (px, py) = data[j]
                plt.scatter(x=px, y=py)
            plt.imshow(X=im)
        elif len(data.target_type) == 2:
            if data.target_type[0] == "category":
                im, (lab, (px, py)) = data[j]
            elif data.target_type[0] == "annotation":
                im, ((px, py), lab) = data[j]
            plt.title(label=lab)
            plt.imshow(X=im)
            plt.scatter(x=px, y=py)
    plt.tight_layout()
    plt.show()

show_images(data=category_data, main_title="category_data")
show_images(data=annotation_data, main_title="annotation_data")
show_images(data=all_data, main_title="all_data")