*Memos:
- My post explains Caltech 101.
- My post explains Caltech256().
Caltech101() can use Caltech 101 dataset as shown below:
*Memos:
- The 1st argument is
root(Required-Type:strorpathlib.Path). *An absolute or relative path is possible. - The 2nd argument is
target_type(Optional-Default:"category"-Type:strortupleorlistofstr): *Memos:-
"category"and/or"annotation"can be set to it. - 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 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) toroot. - If it's
Trueand the dataset is already downloaded, it's extracted. - If it's
Trueand the dataset is already downloaded and extracted, nothing happens. - It should be
Falseif the dataset is already downloaded and extracted because it's faster. - scipy may be required to load target files from
.matfiles. - gdown may be required to download the dataset.
- You can manually download and extract the dataset(
101_ObjectCategories.tar.gzandAnnotations.tar) from here todata/caltech101/.
- If it's
- About the label from the categories(classes) for 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), category_data.categories # (101, # ['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', ..., 'windsor_chair', 'wrench', 'yin_yang']) len(category_data.annotation_categories), category_data.annotation_categories # (101, # ['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', ..., 'windsor_chair', 'wrench', 'yin_yang']) 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[435] # (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=290x334>, # (1, array([[64.52631579, 95.31578947, 123.26315789, 149.31578947, ...], # [15.42105263, 8.31578947, 10.21052632, 28.21052632, ...]]))) all_data[870] # (<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=192x128>, # (2, array([[2.96536524, 7.55604534, 19.45780856, 33.73992443, ...], # [23.63413098, 32.13539043, 33.83564232, 8.84193955, ...]]))) 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) if len(data.target_type) == 1: if data.target_type[0] == "category": for i, j in enumerate(iterable=ims, start=1): plt.subplot(2, 5, i) im, lab = data[j] plt.imshow(X=im) plt.title(label=lab) elif data.target_type[0] == "annotation": for i, j in enumerate(iterable=ims, start=1): plt.subplot(2, 5, i) im, (px, py) = data[j] plt.imshow(X=im) plt.scatter(x=px, y=py) plt.imshow(X=im) elif len(data.target_type) == 2: if data.target_type[0] == "category": for i, j in enumerate(iterable=ims, start=1): plt.subplot(2, 5, i) im, (lab, (px, py)) = data[j] plt.imshow(X=im) plt.title(label=lab) plt.scatter(x=px, y=py) elif data.target_type[0] == "annotation": for i, j in enumerate(iterable=ims, start=1): plt.subplot(2, 5, i) im, ((px, py), lab) = data[j] plt.imshow(X=im) plt.scatter(x=px, y=py) plt.title(label=lab) 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") 
Top comments (0)