Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

It can train on the VOC format dataset.Just can not run it directly on the darket #205

Open
SpongeBab opened this issue Mar 24, 2021 · 3 comments

Comments

@SpongeBab
Copy link

SpongeBab commented Mar 24, 2021

You can see at #8

image
image
image
image
image

hi@WongKinYiu.
this is the generated png during my train.
is this is normal?
some Bbox is correct but some is abnormal.
can you help me ?
please.

@SpongeBab
Copy link
Author

and this is the test result
predictions
predictions
predictions

@SpongeBab
Copy link
Author

@WongKinYiu
this is my xml.

<annotation>
    <folder>E:\Desk\demo</folder>
    <filename>02_20201017135000_2.jpg</filename>
    <path>E:\Desk\demo\02_20201017135000_2.jpg</path>
    <source>
        <database>desk</database>
    </source>
    <size>
        <width>1920</width>
        <height>1080</height>
        <depth>3</depth>
    </size>
    <segmented>0</segmented>
    <object>
        <name>studentDesk</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>1162</xmin>
            <ymin>858</ymin>
            <xmax>1499</xmax>
            <ymax>1061</ymax>
        </bndbox>
    </object>
    <object>

this is my .txt label
0 0.69296875 0.888425925925926 0.17552083333333332 0.18796296296296297
0 0.7640625 0.6509259259259259 0.12291666666666666 0.12407407407407407
0 0.8020833333333334 0.4930555555555556 0.09479166666666666 0.075
0 0.79453125 0.3888888888888889 0.01614583333333333 0.037037037037037035
0 0.8671875 0.3388888888888889 0.015625 0.022222222222222223
0 0.8341145833333333 0.2740740740740741 0.0171875 0.014814814814814815
0 0.8549479166666667 0.2490740740740741 0.04739583333333333 0.02777777777777778
.....

and i reproduce my bounding box by my xml files.
图片

where is the error?
hope to your reply!

@SpongeBab
Copy link
Author

latest.
#8

@SpongeBab SpongeBab changed the title is it a bug? train batch png .is this normal? Now I can confirm it can not train with VOC dataset(并不能在voc数据集训练) Mar 30, 2021
@SpongeBab SpongeBab changed the title Now I can confirm it can not train with VOC dataset(并不能在voc数据集训练) It can train on the VOC format dataset👏。just can not run it directly on the darket Apr 2, 2021
@SpongeBab SpongeBab changed the title It can train on the VOC format dataset👏。just can not run it directly on the darket It can train on the VOC format dataset👏。Just can not run it directly on the darket Apr 3, 2021
@SpongeBab SpongeBab changed the title It can train on the VOC format dataset👏。Just can not run it directly on the darket It can train on the VOC format dataset👏.Just can not run it directly on the darket Apr 3, 2021
@SpongeBab SpongeBab changed the title It can train on the VOC format dataset👏.Just can not run it directly on the darket It can train on the VOC format dataset.Just can not run it directly on the darket Nov 18, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant