Comments (7)
@Zebrocode I just tested with the following environment:
python 3.6.7
pytorch 1.0.0 (py3.6_cuda90_cudnn7_1)
torchvison 0.2.2
It works.
from deep-exemplar-based-colorization.
Thanks for the help. And because i want to run the similarity_subnet and colorization_subnet together.And caffe needs CUDA 8.0. So i tryed following environment and run them together.
my OS is win10.
python 3.7.2
pytorch 1.0.1(CUDA 8.0 cudnn 5.1)
torchvision 0.1.8
i think it may facilitate others who want to run your whole project in the same OS. ^-^
from deep-exemplar-based-colorization.
sorry about bother you again,i meet a problem when i want to run deep_image_analogy.exe to reproduce a new bidirecton mapping function. logs as follow:
from deep-exemplar-based-colorization.
@Zebrocode
For the error, please refer to msracver/Deep-Image-Analogy#11, and your problem may be solved by disabling TDR.
from deep-exemplar-based-colorization.
I find disable TDR can't help. And the exe is complied by myself from the project i download from your repository. I can just solve it by noting the check called CUDA_POST_KERNEL_CHECK in pooling_layer.cu.
But if i use your demo exe directly,the project can run well with the TDR disabled.
from deep-exemplar-based-colorization.
@Zebrocode Did you enable or disable CUDA_POST_KERNEL_CHECK? What kind of Cuda error did you meet?
from deep-exemplar-based-colorization.
I didn't do anything to enable or disable CUDA_POST_KERNEL_CHECK and don't know how to enable or disable it.
The error is just the same as above let me show you again.
so i have no other better idea. i can just note the code in pooling_layer.cu:
After I note the two places and recomplie caffe and deep_image_analogy again, the error disappeared.
from deep-exemplar-based-colorization.
Related Issues (20)
- what is the construction of combo file? HOT 4
- migrate to pytorch or keras HOT 1
- 请问您近期是否有打算将similarity_subnet迁移到基于python语言的框架呢? HOT 1
- Color Transfer HOT 2
- Deep Image Analogy for Colorization HOT 4
- About Flow and Combo files HOT 4
- Any plan to publish your filtered Hollywood2 dataset? HOT 1
- Check failed: error == cudaSuccess (2 vs. 0) out of memory HOT 4
- The meaning of theta parameter in the paper HOT 1
- Average run time. HOT 3
- About PSNR(dB) value
- Is it possible to running on CUDA 10.2? HOT 1
- Training code
- Need to change caffe source code for correct running
- How to Get Reference Image about ImageNet 10k subset? HOT 2
- (-215:Assertion failed) !_src.empty() in function 'cvtColor'
- Inquiry on input format HOT 1
- what is in1_ref1.combo? HOT 1
- Infrared image colorization HOT 5
- Reduce model size
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 deep-exemplar-based-colorization.