Comments (4)
@304883563 请问您有LIVE或其他数据集可以分享下吗[email protected],非常感谢!!!
from dvqa.
我需要测试的视频是yuv大小大约是433M 1366x768 大约280多帧。使用CPU机器进行评分。机器内存4核32G。 运行一段时间。提示需要52G的内存。为何需要如此之大的内存?能否解答下。或者是否有参数可以调节。
首先,不建议使用CPU来跑模型,就算是解决了内存问题,CPU的运行时间会是GPU的几十倍。现在的代码是没有任何针对CPU的优化。当然,GPU模式也有很大的优化空间
直观地来说,有几个原因导致内存开销大。我们对YUV使用sliding windows采样,而且是有overlap的方式。模型运行期间也会产生高纬度的tensor,所以内存消耗比较大。另外,这是一个全参考模型,内存消耗又会加倍。数据预加载也会同步消耗内存。
在不改代码的前提下,一个比较简单的方式是减少单个测试序列的帧数,CPU/GPU内存消耗跟帧数成线性。
from dvqa.
@304883563 请问您有LIVE或其他数据集可以分享下吗[email protected],非常感谢!!!
需要你去数据集官网下载。一般这种数据集不允许redistribute。
from dvqa.
@haiqwang 你好,请问GPU运行情况下对显存占用有什么优化操作推荐我们去研究?我12G的显存,跑1980x1080分辨率的视频有点吃力。
from dvqa.
Related Issues (20)
- the performance when using some filters (USM) is not good HOT 1
- ”dis" and "ref" in dataset json file HOT 3
- 请问有小白使用DVQA的使用指南吗? HOT 12
- Minimum hardware requirement for the evaluation of 720p/1080p video HOT 5
- RuntimeError: The size of tensor a (109) must match the size of tensor b (71) at non-singleton dimension 2 HOT 3
- The performance on LIVE-VQA dataset. HOT 6
- 有预训练好的模型吗,想看看效果
- The question of the training setting of C3DVQA HOT 10
- dataset中json里的mos值是怎么获取?
- How to output the number of FLOPs of this model?
- 请问您有csiq数据集的下载地址吗,找了好久,都没找到。可以给个网盘地址或者发送到邮箱[email protected]。非常感谢。 HOT 5
- How is the MOS label in the dataset videoset mapped? This paper only uses video in yuv format, if only mp4 format is used, is there any performance impact? HOT 2
- Could you provide the download link of video quality datasets? HOT 2
- 训练一个自己的DVQA模型,理想的样本数量是多少? HOT 2
- a question about our eval results HOT 2
- The file(.json) about the dataset information of the LIVE and CSIQ HOT 2
- any pretrained models? HOT 1
- could you introduce some about the dataset size, training environments, training speed HOT 2
- How to use it by CPU? 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 dvqa.