DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on

CocoCaptions in PyTorch (2)

Buy Me a Coffee

*Memos:

  • My post explains CocoCaptions() using train2014 with captions_train2014.json, instances_train2014.json and person_keypoints_train2014.json, val2014 with captions_val2014.json, instances_val2014.json and person_keypoints_val2014.json and test2017 with image_info_test2014.json, image_info_test2015.json and image_info_test-dev2015.json.
  • My post explains CocoCaptions() using train2017 with stuff_train2017.json, val2017 with stuff_val2017.json, stuff_train2017_pixelmaps with stuff_train2017.json, stuff_val2017_pixelmaps with stuff_val2017.json, panoptic_train2017 with panoptic_train2017.json, panoptic_val2017 with panoptic_val2017.json and unlabeled2017 with image_info_unlabeled2017.json.
  • My post explains CocoDetection() using train2014 with captions_train2014.json, instances_train2014.json and person_keypoints_train2014.json, val2014 with captions_val2014.json, instances_val2014.json and person_keypoints_val2014.json and test2017 with image_info_test2014.json, image_info_test2015.json and image_info_test-dev2015.json.
  • My post explains CocoDetection() using train2017 with captions_train2017.json, instances_train2017.json and person_keypoints_train2017.json, val2017 with captions_val2017.json, instances_val2017.json and person_keypoints_val2017.json and test2017 with image_info_test2017.json and image_info_test-dev2017.json.
  • My post explains CocoDetection() using train2017 with stuff_train2017.json, val2017 with stuff_val2017.json, stuff_train2017_pixelmaps with stuff_train2017.json, stuff_val2017_pixelmaps with stuff_val2017.json, panoptic_train2017 with panoptic_train2017.json, panoptic_val2017 with panoptic_val2017.json and unlabeled2017 with image_info_unlabeled2017.json.
  • My post explains MS COCO.

CocoCaptions() can use MS COCO dataset as shown below. *This is for train2017 with captions_train2017.json, instances_train2017.json and person_keypoints_train2017.json, val2017 with captions_val2017.json, instances_val2017.json and person_keypoints_val2017.json and test2017 with image_info_test2017.json and image_info_test-dev2017.json:

from torchvision.datasets import CocoCaptions

cap_train2017_data = CocoCaptions(
    root="data/coco/imgs/train2017",
    annFile="data/coco/anns/trainval2017/captions_train2017.json"
)

ins_train2017_data = CocoCaptions(
    root="data/coco/imgs/train2017",
    annFile="data/coco/anns/trainval2017/instances_train2017.json"
)

pk_train2017_data = CocoCaptions(
    root="data/coco/imgs/train2017",
    annFile="data/coco/anns/trainval2017/person_keypoints_train2017.json"
)

len(cap_train2017_data), len(ins_train2017_data), len(pk_train2017_data)
# (118287, 118287, 118287)

cap_val2017_data = CocoCaptions(
    root="data/coco/imgs/val2017",
    annFile="data/coco/anns/trainval2017/captions_val2017.json"
)

ins_val2017_data = CocoCaptions(
    root="data/coco/imgs/val2017",
    annFile="data/coco/anns/trainval2017/instances_val2017.json"
)

pk_val2017_data = CocoCaptions(
    root="data/coco/imgs/val2017",
    annFile="data/coco/anns/trainval2017/person_keypoints_val2017.json"
)

len(cap_val2017_data), len(ins_val2017_data), len(pk_val2017_data)
# (5000, 5000, 5000)

test2017_data = CocoCaptions(
    root="data/coco/imgs/test2017",
    annFile="data/coco/anns/test2017/image_info_test2017.json"
)

testdev2017_data = CocoCaptions(
    root="data/coco/imgs/test2017",
    annFile="data/coco/anns/test2017/image_info_test-dev2017.json"
)

len(test2017_data), len(testdev2017_data)
# (40670, 20288)

cap_train2017_data[2]
# (<PIL.Image.Image image mode=RGB size=640x428>,
#  ['A flower vase is sitting on a porch stand.',
#   'White vase with different colored flowers sitting inside of it. ',
#   'a white vase with many flowers on a stage',
#   'A white vase filled with different colored flowers.',
#   'A vase with red and white flowers outside on a sunny day.'])

cap_train2017_data[47]
# (<PIL.Image.Image image mode=RGB size=640x427>,
#  ['A man standing in front of a microwave next to pots and pans.',
#   'A man displaying pots and utensils on a wall.',
#   'A man stands in a kitchen and motions towards pots and pans. ',
#   'a man poses in front of some pots and pans ',
#   'A man pointing to pots hanging from a pegboard on a gray wall.'])

cap_train2017_data[64]
# (<PIL.Image.Image image mode=RGB size=480x640>,
#  ['A little girl holding wet broccoli in her hand. ',
#   'The young child is happily holding a fresh vegetable. ',
#   'A little girl holds a hand full of wet broccoli. ',
#   'A little girl holds a piece of broccoli towards the camera.',
#   'a small kid holds on to some vegetables '])

ins_train2017_data[2] # Error

ins_train2017_data[47] # Error

ins_train2017_data[67] # Error

pk_train2017_data[2]
# (<PIL.Image.Image image mode=RGB size=640x428>, [])

pk_train2017_data[47] # Error

pk_train2017_data[64] # Error

cap_val2017_data[2]
# (<PIL.Image.Image image mode=RGB size=640x483>,
#  ['Bedroom scene with a bookcase, blue comforter and window.',
#   'A bedroom with a bookshelf full of books.',
#   'This room has a bed with blue sheets and a large bookcase',
#   'A bed and a mirror in a small room.',
#   'a bed room with a neatly made bed a window and a book shelf'])

cap_val2017_data[47]
# (<PIL.Image.Image image mode=RGB size=640x480>,
#  ['A group of people cutting a ribbon on a street.',
#   'A man uses a pair of big scissors to cut a pink ribbon.',
#   'A man cutting a ribbon at a ceremony ',
#   'A group of people on the sidewalk watching two young children.',
#   'A group of people holding a large pair of scissors to a ribbon.'])

cap_val2017_data[64]
# (<PIL.Image.Image image mode=RGB size=375x500>,
#  ['A man and a women posing next to one another in front of a table.',
#   'A man and woman hugging in a restaurant',
#   'A man and woman standing next to a table.',
#   'A happy man and woman pose for a picture.',
#   'A man and woman posing for a picture in a sports bar.'])

ins_val2017_data[2] # Error

ins_val2017_data[47] # Error

ins_val2017_data[64] # Error

pk_val2017_data[2]
# (<PIL.Image.Image image mode=RGB size=640x483>, [])

pk_val2017_data[47] # Error

pk_val2017_data[64] # Error

test2017_data[2]
# (<PIL.Image.Image image mode=RGB size=640x427>, [])

test2017_data[47]
# (<PIL.Image.Image image mode=RGB size=640x406>, [])

test2017_data[64]
# (<PIL.Image.Image image mode=RGB size=640x427>, [])

testdev2017_data[2]
# (<PIL.Image.Image image mode=RGB size=640x427>, [])

testdev2017_data[47]
# (<PIL.Image.Image image mode=RGB size=480x640>, [])

testdev2017_data[64]
# (<PIL.Image.Image image mode=RGB size=640x480>, [])

import matplotlib.pyplot as plt

def show_images(data, ims, main_title=None):
    file = data.root.split('/')[-1]
    fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(14, 8))
    fig.suptitle(t=main_title, y=0.9, fontsize=14)
    x_crd = 0.02
    for i, axis in zip(ims, axes.ravel()):
        if data[i][1]:
            im, anns = data[i]
            axis.imshow(X=im)
            y_crd = 0.0
            for j, ann in enumerate(iterable=anns):
                text_list = ann.split()
                if len(text_list) > 9:
                    text = " ".join(text_list[0:10]) + " ..."
                else:
                    text = " ".join(text_list)
                plt.figtext(x=x_crd, y=y_crd, fontsize=10,
                            s=f'{j}:\n{text}')
                y_crd -= 0.06
            x_crd += 0.325
            if i == 2 and file == "val2017":
                x_crd += 0.06
        elif not data[i][1]:
            im, _ = data[i]
            axis.imshow(X=im)
    fig.tight_layout()
    plt.show()

ims = (2, 47, 64)

show_images(data=cap_train2017_data, ims=ims,
             main_title="cap_train2017_data")
show_images(data=cap_val2017_data, ims=ims, 
             main_title="cap_val2017_data")
show_images(data=test2017_data, ims=ims,
            main_title="test2017_data")
show_images(data=testdev2017_data, ims=ims, 
            main_title="testdev2017_data")
Enter fullscreen mode Exit fullscreen mode

Image description

Image description

Image description

Image description

Sentry image

Hands-on debugging session: instrument, monitor, and fix

Join Lazar for a hands-on session where you’ll build it, break it, debug it, and fix it. You’ll set up Sentry, track errors, use Session Replay and Tracing, and leverage some good ol’ AI to find and fix issues fast.

RSVP here →

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

👋 Kindness is contagious

Please leave a ❤️ or a friendly comment on this post if you found it helpful!

Okay