Comments (11)
Indeed. Seems the code require more than 10 GB to run.
However the maximum memory usage reported by torch.cuda.max_memory_allocated()
is less than 9 GB, which is weird.
I'll check this problem.
For now, you can reduce the number of views by reducing nsrc=4
in eval.sh
. (Which will make performance drop a little bit)
Or you can try to delete some intermediate tensors and free up memory on GPU using del tensor1
and torch.cuda.empty_cache()
.
Or, probably the easiest way, run it on a 11GB GPU:)
Jiayu.
from cvp-mvsnet.
Hi @lauraset
Training on higher resolution can provide slightly better performance and better generalization ability.
However it consumes more GPU memory. Training the network on 640x512 requires at least 16GB GPUs.
Jiayu.
from cvp-mvsnet.
I use to get an Error while running the eval.sh script!
runtime error: CUDA out of memory. Tried to allocate 3.05 GiB (GPU 0; 9.78 GiB total capacity; 5.01 GiB already allocated; 2.51 GiB free; 5.54 GiB reserved in total by PyTorch)
from cvp-mvsnet.
It should be able to run on 10GB GPU.
The maximum vram required is around 9GB.
Is there any other process that are using your GPU memory?
You can use nvidia-smi
to check that.
Cheers,
Jiayu.
from cvp-mvsnet.
Hi @JiayuYANG, It think there is nothing else that is running on the GPU. I am running the code in a docker-machine
The below is the output from the nvidia-smi command
[
And while I run the eval.sh, I get the output as below
from cvp-mvsnet.
Hi Jiayu,
Thanks for the reply, i will look into it as you have mentioned.
Cheers
from cvp-mvsnet.
Hi jiayu, is it possible to run the CVPNet with a 11 GB GPU? I tried it, but failed.
from cvp-mvsnet.
Hi @lauraset
Yes, it should be able to run on 11GB GPU.
Jiayu.
from cvp-mvsnet.
Thanks for your reply. Yes, I found that it's possible to run it with the provided DTU images (160 x 128), but it seems that the network can't work with images (384 x 768) even with a batch size of 1. I note that there are high resolution DTU images and depth images, but I am not clear whether the network (CVPNet) trained with high resolution DTU images (for example, 640 x 512) will outperform that trained with low resolution images (160 x 128). Have you ever tried it?
from cvp-mvsnet.
Thanks for your help, Jiayu. I notice that you adopted the image pyramid method to reduce the memory requirement in the CVPNet. But this way still uses the fixed cost volume (e.g., D =192), compared to the adjustable one used in the cascade mvsnet. Is it the limitation to apply the CVPNet to high resolution images?
from cvp-mvsnet.
Hi @lauraset
I suggest you to read our paper more carefully.
One of our main contribution in CVP-MVSNet is the use of cost volume pyramid instead of fixed cost volume.
It enables us to inference high resolution depth map with less memory consumption.
It is similar to the concurrent work cascade mvsnet.
Jiayu.
from cvp-mvsnet.
Related Issues (20)
- Can you provide your 3D point clouds for DTU test set?
- Normal Map HOT 2
- returned value in calDepthHypo HOT 3
- How to load checkpoint(.ckpt) in test code? HOT 1
- ERROR HOT 3
- generalization ability(泛化能力) of neural network based MVS HOT 2
- Tank test
- RuntimeError: cuda runtime error (710) : device-side assert triggered at
- 自采数据 HOT 1
- Pixel Interval
- Running inference on 8GB RTX 3070
- 自采数据集的参数设置
- License
- What is "disp.dmb" in "outputs_pretrained/fusibile_fused"?How to understand this?
- datasets request
- 如何使用自己录制的数据集
- Found 0.00 million points HOT 1
- Matlab Evaluation
- Thank you for your work. Where can I download the supplementary materials mentioned in your paper?
- Environmental conflicts
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 cvp-mvsnet.