Comments (4)
想问为什么没有使用torch自带的dataloader,自己写的列表读的太慢了,而且占用内存太高
from dface.
@libohit 我用了自己的数据,没有用wider。 训练数据的数量大概6万张图片,在加载数据过程中很慢,然后生成样本保存在本地的时候直接把硬盘存满了。正样本加上负样本就已经有五百万了。这个代码里面加载数据的部分没有使用pytorch的dataloader的api,而是自己实现的,不知道作者为什么不使用api而是选择自己去实现数据输入。
from dface.
我用wider训练没有这么慢呢!
from dface.
@Ghustwb 加载数据可以选用队列(pytorch内置队列功能), 硬件方面推荐使用闪存吧,文件系统推荐ext4或者F2FS。
from dface.
Related Issues (20)
- Loss variates a lot during training
- How long does it take to train RNet?
- How's the inference speed on CPU?
- bbox loss激增问题 HOT 2
- TypeError: 'float' object is not subscriptable HOT 4
- Onet ValueError HOT 1
- Runtime error:zero-dimensional tensor(at position 0) cannot be contatenated HOT 3
- loss function
- TypeError: float() argument must be a string or a number, not 'map' HOT 2
- ValueError: negative dimensions are not allowed HOT 5
- Error gen_Rnet_train_data.py
- Do this project have train/recognise module?
- RuntimeError: Expected object of scalar type Double but got scalar type Float for argument #2 'weight' HOT 2
- Enviroment issues
- Package versions HOT 1
- Encounter environment bug-->OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized. HOT 2
- Why not use the resenet API in keras HOT 1
- gen_Onet_train_data.py ValueError: negative dimensions are not allowed HOT 1
- RuntimeError: expected scalar type Double but found Float HOT 2
- RuntimeError: Input type (double) and bias type (float) should be the same HOT 4
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 dface.