GithubHelp home page GithubHelp logo

Comments (5)

zibuyu2018 avatar zibuyu2018 commented on July 23, 2024

i have load this https://www.dropbox.com/s/oeu149j8qtbs1x0/SegmentationClassAug.zip?dl=0 and put this in VOCdevkit/VOC2012/SegmentationClassAug/.png. but there have inconsitency label and still have this problom

thank you,
It doesn't seem to be complete, but I solved the problem by deleting some images in the txt file that I couldn't find in the SegmentationClassAug file.

from deeplab-v2--resnet-101--tensorflow.

zhengyang-wang avatar zhengyang-wang commented on July 23, 2024

The augmented PASCAL VOC 2012 dataset with 10582 images for training and 1449 images for validation. Here is a download link of augmented labels: https://www.dropbox.com/s/oeu149j8qtbs1x0/SegmentationClassAug.zip?dl=0

#7

from deeplab-v2--resnet-101--tensorflow.

heyitsguay avatar heyitsguay commented on July 23, 2024

Hi @zhengyang-wang! I have followed the instructions you provided in your most recent comment, but I still get errors about files not being found. The first is as follows, with a little initial context so you can see when it happens:

('after start block:', TensorShape([Dimension(10), Dimension(81), Dimension(81), Dimension(64)]))
('after block1:', TensorShape([Dimension(10), Dimension(81), Dimension(81), Dimension(256)]))
('after block2:', TensorShape([Dimension(10), Dimension(41), Dimension(41), Dimension(512)]))
('after block3:', TensorShape([Dimension(10), Dimension(41), Dimension(41), Dimension(1024)]))
('after block4:', TensorShape([Dimension(10), Dimension(41), Dimension(41), Dimension(2048)]))
-----------build decoder-----------
('after aspp block:', TensorShape([Dimension(10), Dimension(41), Dimension(41), Dimension(21)]))
Restored model parameters from ./deeplab_resnet_init.ckpt
###### This part right here
2018-06-20 00:01:55.388202: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at whole_file_read_ops.cc:114 : Not found: /home/matt/VOC2012/SegmentationClassAug/2008_003519.png; No such file or directory

I went and looked in SegmentationClassAug, and found that the files had names beginning with 2007_, and neither 2008_003519.png nor 2007_003519.png exists. Can you help me reconcile this discrepancy?

Thanks,
Matt

from deeplab-v2--resnet-101--tensorflow.

StewartSethA avatar StewartSethA commented on July 23, 2024

My solution was just to delete the offending lines from the dataset/train.txt file.
train.txt

from deeplab-v2--resnet-101--tensorflow.

zhengyang-wang avatar zhengyang-wang commented on July 23, 2024

I have 12031 files in SegmentationClassAug. Please check.

from deeplab-v2--resnet-101--tensorflow.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.