Comments (6)
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.
from context-transformer.
Thank you for your answer. But when I run the .sh script to download Main20xx.tar, the link about Main20xx.tar is not found.
from context-transformer.
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.
from context-transformer.
OK, I try it again. Thank you so much!!!
from context-transformer.
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?
from context-transformer.
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.
from context-transformer.
Related Issues (16)
- Issue about the COCO dataset HOT 7
- cannot import name '_mask' from 'utils.pycocotools' HOT 9
- how to split voc data HOT 3
- How can I reproduce experiment in limit cuda memory HOT 3
- Issue about "trainval_1shot.txt" HOT 2
- How to train model with 1 GPU? HOT 10
- How to train on a customized dataset? HOT 1
- About Figure.5 in your paper HOT 4
- Comparing with SOTA methods HOT 1
- demo.py HOT 2
- size 512 error. HOT 1
- [Errno 2] No such file or directory: './data/COCO/annotations/instances_valminusminival2014.json' HOT 5
- Pretraining RFBNet on source domain dataset COCO60, it shows loss nan HOT 7
- src_cls_dim HOT 1
- Can't get the simmilar mAP of VOC split1 at phase1 under incremental setting.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from context-transformer.