Comments (25)
Sorry,
USE \\ please not \
Your pickle file is
0
0
That means your computer find no directory.
from fcn.tensorflow.
@chankeh
hi chankeh,
Thank you for your suggesions, but i still have the same question:
ValueError: Cannot feed value of shape (0,) for Tensor 'input_image:0', which has shape '(?, 224, 224, 3)'
i have tried both, but didn't work:
1.SceneParsing_folder = os.path.splitext(DATA_URL.split("\")[-1])[0]
filename = os.path.splitext(f.split("\")[-1])[0]
2.SceneParsing_folder = os.path.splitext(DATA_URL.split("/")[-1])[0]
filename = os.path.splitext(f.split("\")[-1])[0]
I am a learner,my computer is windows tf0.12 gpu1060, could you help me?
best regards
from fcn.tensorflow.
I have solved some problems both in ubuntu and Windows10 , and now the code can run very well.
some tips you should know.
1.unzip the dataset and download the mat file
2.you should know the difference between linux and window, such as os.path.splitext() function,you must replace '/' with '\'(use two'\',caution) in windows.
3.use a computer which equiped with gpu.
I think , if you solved above problems , the code will be runed well.
2017/05/11 in ShenYang,China,Northeastern University.
from fcn.tensorflow.
Before generating "MITSceneParsing.pickle", I use '\\' instead of '/' (line 54 in "read_MITSceneParsingData.py"), and solve the problem.
from fcn.tensorflow.
@chankeh
hello
Sorry to bother you,I use '\' instead of '/' .But it doesn't work.I use WIN10 .It gives the same error.Do you know the reason?
Thank you very much!
from fcn.tensorflow.
@chankeh
hello,I delete 'not' and it find the file like this .but does it mean working well?
from fcn.tensorflow.
Did you run on windows?
The output of your pickle file is
0
0
which means that when you read image lists , your system found nothing
Please check the os.path.splitext() function in your read_MITSceneParsingData.py file.
If you are windows it should be "\"instead of "/"
please reference to issue 9
from fcn.tensorflow.
from fcn.tensorflow.
@eserercanakin Did the solution posted above solve the problem? Please close issue if it did.
Thanks.
from fcn.tensorflow.
Closing due to inactivity.
from fcn.tensorflow.
@Patickk
i also used tf0.12rc ,but some problems you just raised doesn't occur.
please check whether your path is right.
and my path is like this,
FCN.tensorflow-master\Data_zoo\MIT_SceneParsing
FCN.tensorflow-master\Model_zoo
i think maybe it is the path error.
from fcn.tensorflow.
@chankeh
thanks bro,and I have sove the problem:
I deleted the data, run the code ,and it worked!.....lol, may be there is a bug on my old data
so ,i have a new problem:
training_records = result['training']
TypeError: 'NoneType' object is not subscriptable
i didn't find the answer to solve this ,and there is no questions about this, do you think it's also a bug?
best regards
from fcn.tensorflow.
@Patickk
did you download this data ? ----> MIT_SceneParsing
this is the trainning and test dataset , and you should put it in the folder, Data_zoo,which should locate in the root path,the same path with your python file.(Data_zoo' path is the same as python file )
and you should know that the difference between linux and wndows(if you are using linux,you should use '/' ,while if you are using windows ,you shoule use '\'(two '\',because it is transferred by the system here.))
the problems you just raised is still the path problem
from fcn.tensorflow.
hellohi
some questions i can't find out the reason. First I run the code with cpu, does it allowed? and i have replaced '/' with '\' , the dataset is under the right path. it still the same error:
from fcn.tensorflow.
@wxwhu
it seems that your data'path is wrong.
structure like this,
from fcn.tensorflow.
@chankeh
this is my path.I don't know where it goes wrong.
from fcn.tensorflow.
@wxwhu
path like this,
from fcn.tensorflow.
@wxwhu
as the following,
from fcn.tensorflow.
@chankeh thaks,but It works bad,but it gives the same error.
from fcn.tensorflow.
@wxwhu
yes,it means right
from fcn.tensorflow.
@Patickk Hello, i ran into the same problem you do about the TypeError: 'NoneType' object is not subscriptable.
Wonder if you ever fixed this problem,tks.
from fcn.tensorflow.
@chankeh
hello,I delete 'not' and it find the file like this .but does it mean working well?
your method is working. I think it is because we have run FCN.py. So there is a file "MITSceneParsing.pickle". If we delete it, we need not delete "not''
from fcn.tensorflow.
I had the same problem that 'ValueError: Cannot feed value of shape (0,).....'
Then I found the size of the file 'MITSceneParsing.pickle' is just 1KB,which means maybe nothing in it.
When I delete it and run the code again, it work without the ValueError !
So I suppose that when you change '/' into '' in windows, you should delete the MITSceneParsing.pickle generated before and run the code to regenerate it.
from fcn.tensorflow.
Hey, to anyone still subscribed to this thread, please help me out with my issue#128.
I'm getting a ValueError: Unknown mat file type, version 110, 116
.
I have correctly structured my directory as suggested, and am on Ubuntu 20.04.
Any help is appreciated, thanks.
from fcn.tensorflow.
from fcn.tensorflow.
Related Issues (20)
- Why not implement batch normalization?
- Questions about training
- Expected string passed to parameter 'tag' of op 'ImageSummary', got 'input_image_1' of type 'str' instead. HOT 1
- run FCN.py , path wrong HOT 1
- is fusion operation the same as the paper?
- 为什么没有把pool5的结果和最后结果上采样做差值,我看代码只做了pool4和pool3的结果 HOT 1
- 论文中是说最后输入1000张特征图,取1000张特征图中的各像素最大值,为啥这个代码要用3通道呢 HOT 2
- KeyError: 'normalization' HOT 1
- Train the model for face parsing problem HOT 2
- how to train my own dataset?
- Training problem HOT 1
- What is output node's name? HOT 1
- Is anyone could share the trained ckpt???thanks!!!!
- ValueError: Cannot feed value of shape (2, 227, 227, 1, 4) for Tensor 'annotation:0', which has shape '(?, 227, 227, 1)' HOT 2
- Can I use FCN on Windows 10?
- 'NoneType' object is not subscriptable
- i made a reimplement with tensorflow2 HOT 3
- ValueError: Unknown mat file type, version 110, 116 HOT 2
- Logging and Visualizing Training Metrics on Tensorboard
- Implementing GradCam HOT 1
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 fcn.tensorflow.