Comments (3)
Hi, can you try lowering the learning rate and turning off momentum?
-Brandon.
from dcgan-completion.tensorflow.
By dividing the learning rate by 100, and turning off momentum, the loss function decreases better. However, the result is still bad (especially the first picture, which is a selfie from myself, while the other 3 are famous politicians):
In your demo, what is the final loss?
I could not get less than 1500.
I ran the command:
./complete.py /home/ubuntu/dcgan-completion.tensorflow/static/aligned/rawfaces/* --lr 0.0001 --momentum 0.0 --nIter 1200 --outDir /home/ubuntu/dcgan-completion.tensorflow/static/outputimages
from dcgan-completion.tensorflow.
The last three there look much better than before, an adaptive technique would definitely help here. An adaptive one could potentially help the first image so you don't have to tune the learning rate. You could also try changing the lambda
weight. I don't remember the final loss I got.
I'll close this issue for now but let me know if you notice anything else.
-Brandon.
from dcgan-completion.tensorflow.
Related Issues (20)
- Key generator/g_h5/w not found in checkpoint HOT 3
- NotFoundError (see above for traceback): Key generator/g_h6/w not found in checkpoint HOT 2
- ValueError: setting an array element with a sequence. HOT 2
- Getting "in complete assert(isLoaded) AssertionError" when running complete.py on my own checkpoints directory HOT 1
- error while using complete.py
- there is nothing in the folder “sample” after 25 epoch HOT 6
- Why data in one epoch didn't shuffle?
- Key discriminator/d_bn0/beta not found in checkpoint? HOT 8
- OOM error when training data
- NotFoundError (see above for traceback): Key discriminator/d_bn0/beta not found in checkpoint HOT 1
- conditional infilling
- what is the usage of the lowres parameter, why the contextual_loss includes this part
- Bug in code that computes the weighs based on the mask
- Cannot feed value of shape (64, 64, 64) for Tensor 'real_images:0', which has shape '(?, 64, 64, 3)' HOT 1
- Final result after 1000 epochs HOT 2
- how to changing image_size HOT 1
- Sorry But I don't know what exactly mean 'delete the checkpoint directory to train a new model' HOT 1
- Issues while training the model HOT 1
- Training with existing model in checkpoint directory
- Changing image_size error 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 dcgan-completion.tensorflow.