Issue about VOC2007.sh

[sandq]

Issue about VOC2007.sh

[Ze-Yang]

As shown in the README.md, you need to first download the dataset by running the .sh script. If you already have a copy on your server, feel free to skip this step. Then you need to put the Main2007.zip and Main2012.zip under the specified directories accordingly and unzip them to get the *.txt files as few-shot image_id list. Note that this is not optional, otherwise will run into error since Main20xx.zip is not the same as Main20xx.tar downloaded by the .sh script. For details, refer to the info below.

Download VOC2007 trainval & test

# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/VOC2007.sh # <directory>

Download VOC2012 trainval

# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/VOC2012.sh # <directory>

Create symlink for the VOC dataset:

ln -s /path/to/VOCdevkit data/VOCdevkit

Image shots and splits preparation

Move the Main2007.zip and Main2012.zip under data/ folder to data/VOCdevkit/VOC2007/ImageSets/ and data/VOCdevkit/VOC2012/ImageSets/ respectively, and unzip them. Make sure that the .txt files contained in the zip file are under corresponding path/to/Main/ folder.

Hope that it helps. Thanks.

[sandq]

Thank you for your answer. But when I run the .sh script to download Main20xx.tar, the link about Main20xx.tar is not found.

[Ze-Yang]

I have tried the links just now and they work fine. I think you can try it again. If fail, I suggest you can copy the links to a brower and download them manually.

Hope it helps. Thanks.

[sandq]

OK, I try it again. Thank you so much!!!

[linsongxue]

I have tried the links just now and they work fine. I think you can try it again. If fail, I suggest you can copy the links to a brower and download them manually.

Hope it helps. Thanks.

Hello
I tried to copy the links to a brower and download them manually but it told 404 not found.
Was that deleted?

[Ze-Yang]

Thank you for pointing out this issue. It is actually a redundant step. I substitute it with the manual instructions Image shots and splits preparation in Readme.md so that you are aware of the modifications of the original dataset (some .txt files are added). I have deleted the redundant links in the .sh scripts and updated the repo. Thanks.