Comments (11)
ok. I've seen the same problem in the previous issues. I'll try to add the batchsize up to 16,and try again. And I wish it will work.
from fcn.tensorflow.
@ChinaYi Maybe you can use "logs/images/Image_Cmaped.ipynb" to visualize your output.
from fcn.tensorflow.
@yeshenlin thanks, I've tried this, but did not work, actually, it turns an all-black png to an all-blue one.
from fcn.tensorflow.
@ChinaYi Is it possible that the model hasn't been trained for enough epochs?
from fcn.tensorflow.
@shekkizh thanks for your help. My iteration times are set to 1e+5, and the best valid_loss is 0.566078. Results are similiar to groud_truth, but not enough comparing to your report. Is there any possible reasons?
from fcn.tensorflow.
Hi @ChinaYi : I am experiencing the same problem as you previously got. After training for 100K (default) iterations, the prediction image is just black. Did you do anything special to fix this issue?
Step: 99800, Train_loss:3.27614
Step: 99810, Train_loss:4.61153
Step: 99820, Train_loss:3.18354
Step: 99830, Train_loss:2.48784
Step: 99840, Train_loss:2.74431
Step: 99850, Train_loss:3.29662
Step: 99860, Train_loss:3.19142
Step: 99870, Train_loss:4.58435
Step: 99880, Train_loss:2.86515
Step: 99890, Train_loss:3.80537
Step: 99900, Train_loss:2.84969
Step: 99910, Train_loss:3.47618
Step: 99920, Train_loss:3.40244
Step: 99930, Train_loss:3.72526
Step: 99940, Train_loss:3.00145
Step: 99950, Train_loss:3.51405
Step: 99960, Train_loss:2.82784
Step: 99970, Train_loss:2.75893
Step: 99980, Train_loss:2.42421
Step: 99990, Train_loss:3.21162
Step: 100000, Train_loss:2.66081
from fcn.tensorflow.
@placentian it seems that your loss has been fluctuated with the iteration times and haven't reached the bottom. This is not a good training process. You'd better enlarge the batch size and try to reduce to learning rate. I have been suffered from the same issues like you, you got black picture since you have a large loss. cheer up!
from fcn.tensorflow.
Thanks a lot for your encouragement, @ChinaYi . Do I also need to change the iteration to some other numbers (like 200K or 500K)?
What kind of reasonable learning rate and batch size would you recommend by any chance?
from fcn.tensorflow.
I got better results after reducing the learingrate but they are not as good as @shekkizh 's results. Dont know what else we should try.
from fcn.tensorflow.
@placentian can you plot you loss curve? Or paste the Train_loss for each iteration
from fcn.tensorflow.
Maybe I can explain why we got black outputs.
When I run the code on 1 GPU Titan Xp (memory 12GB), the original code's performance is good.(Batchsize=2 ,lr=1e-4,itr=30000)
When I run the code on 2 GPU Titan Xp (memory 24GB), the original code's performance is terrible.(Batchsize=2 ,lr=1e-4,itr=30000).But I changed the Batchsize=8 and lr=1e-4 when itr<20000,lr=1e-5 when lr>20000,the performance is better than run on 1GPU.
So your configuration of computer may affect your results.
So try to change these basic arguments, you will get the satisfied output.
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.