Comments (7)
The above change adds a new argument eps
to run.py such that if the L2 loss goes below eps, the program returns. If at the end of steps
steps, the L2 loss is not less than eps the run fails with that error. Thus another fix is to choose a value for eps
that is less than your L2 loss at the end.
After 100 steps I had an L2 loss of 0.006 (6e-3) so I set my eps to 8e-3 with the following colab code, and it worked. The step after this is to lower epsilon and increase steps to get a better result. The best option would be reverting though as we generally just want to see the best result achieved.
seed = 100 #@param {type:"integer"}
epsilon = 8e-3
noise_type = 'trainable' #@param ['zero', 'fixed', 'trainable']
optimizer = 'adam' #@param ['sgd', 'adam','sgdm', 'adamax']
learning_rate = 0.4 #@param {type:"slider", min:0, max:1, step:0.05}
learning_rate_schedule = 'linear1cycledrop' #@param ['fixed', 'linear1cycle', 'linear1cycledrop']
steps = 750 #@param {type:"slider", min:100, max:1000, step:50}
clear_output()
seed = abs(seed)
print('Estimated Runtime: {}s.\n'.format(round(0.23*steps)+6))
!python run.py \
-seed $seed \
-noise_type $noise_type \
-opt_name $optimizer \
-learning_rate $learning_rate \
-steps $steps \
-lr_schedule $learning_rate_schedule \
-eps $epsilon
from pulse.
Increasing the number of steps would solve the issue.
from pulse.
Not sure if this is the recommended way to fix this, but I had the same problem with a 32x32 image. I upscaled it to 1024x1024 (bicubic, so the result is blurry), and it seemed to work for me.
from pulse.
I got the same error with all the images I tried. But only one of them worked using @udf 's method. Thanks anyway! :)
from pulse.
It seems to have been introduced by this commit ece9211
I ran a test on Face-Depixelizer with it reverted, it worked.
from pulse.
Hi @udf , how did you upscaled your images? I have my input in 128x128, and I was looking to upscale it to 1024x1024. Can you explain a bit?
from pulse.
hi...can anyone please help me know how the downsampling loss is implemented. Is it l1 or l2 loss being used to compare the generated low-resolution and the LR image.
please any1 let me know
from pulse.
Related Issues (20)
- Conda command not found
- Recommended Linux Version?
- Any way to reduce Batch_Size in run.py? HOT 1
- What is "latent tensor" used for?
- NIQE
- Optimization procedure returns the wrong image?
- "conda create -f pulse.yml" failed with "either -n name or -p prefix option required" HOT 3
- Question: Are there any ports of this library to Java/Kotlin? HOT 4
- The speed of the pulse
- run error during test,
- [Windows] Conda - "ResolvePackageNotFound" for some modules HOT 2
- pulse
- how do I use in M1?
- algorithm doesnt perform well on child faces...this is supposed to be a 3 months old :)
- What is the usage of geocross loss? HOT 1
- How to run PULSE from 16*16 to 128*128? HOT 3
- About applicability HOT 1
- pulse with only cpu?
- Pulse
- Pulse Application Usage not working with multi guard
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 pulse.