Comments (8)
We used PyTorch 0.3.1 on NVIDIA TITANX 12G
Hi
I used main.py to train model successfully,
but when I use the trained models & eval.py to test, I got "CUDA error: out of memory"
then I tried the pretrained model you provided in https://drive.google.com/drive/folders/1ahbeoEHkjxoo4NV1wReOmpoRWbl448z-?usp=sharing, I also got "CUDA error: out of memory"
my env:
PyTorch: 0.4.1
Python: 3.5.6 & 2.7.5
GPU: Two Tesla P40(20G), all 40G
from dbpn-pytorch.
from dbpn-pytorch.
We used PyTorch 0.3.1 on NVIDIA TITANX 12G
from dbpn-pytorch.
今年4月份我在gtx1060(6G)下可以运行,现在会出现: RuntimeError: CUDA error: out of memory
from dbpn-pytorch.
@llj666666
Are you getting an error when running "python3 main.py"? I am getting an error "local variable 'input' referenced before assignment". I modified "input" but it didn't work. How can you solve this problem?
from dbpn-pytorch.
I get the same message during evaluation.
CUDA error: out of memory
Any advice?
from dbpn-pytorch.
@Frog-Michael I have the same problem as you, have you solved it?
from dbpn-pytorch.
@jotoy
thank you for your reply
Whether There’s a problem with Python’s multiprocessing where it doesn’t always clean up the child processes properly. Can you give me some suggestions for the solution except the replacement version.
from dbpn-pytorch.
Related Issues (20)
- What's class D_DownBlock(torch.nn.Module) mean?What's num_stages mean?
- The question about train. HOT 3
- I inserted some layers into dbpn.py,and it can be trained successfully.But failed to test. HOT 1
- I inserted some layers into dbpn.py,and it can be trained successfully.But failed to test.
- How to use correctly
- Question in main.py HOT 1
- normalization for DBPNITER
- cannot download zip file in any way
- I trained and eval got black images HOT 3
- what is the size of input ?
- Can't get the same results as in the article with pretrained model. HOT 2
- About training on GAN HOT 1
- Is it appropriate that the last convolutional layer of DBPN has no activation function?
- Training on other datasets HOT 1
- Did you initialize all models with zero 'a'?
- what's real critertion in main.py?
- Questions about the setting of network when denoising.
- Doubt about the patch_size parameter
- Discriminator pretrained model missing
- no valid convolution algorithms available in CuDNN
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 dbpn-pytorch.