Comments (3)
使用原始尺寸的图像做Validation,原始图像不管长宽多少,都可以按比例将其最短边缩放到256,长边是N,然后在这个图像上裁剪最中间的224x224。10 Crops就是在图像里面裁剪10个不同的区域,送入神经网络,然后得到概率然后平均,这样性能会更好。
from densenet-caffe.
@shicai Thanks a lot!
1)每次测试都使用原始图像作为,会比用val_lmdb慢很多,而且没法在训练的同时验证;
或是这样:训练前把256xN裁剪得到的224x224图片变成lmdb,这样10个crop得到10个lmdb。
你是怎么做的? 144 crop时以上方法应该都不行,有什么好办法吗?
2)10个输入得到概率取平均,我感觉不能通过python脚本实现,是不是要修改caffe源码?
3)googlenet和resnet等论文里的ensemble model是不是也是多个模型输入取概率平均?
PS:大神能微博私信你吗
from densenet-caffe.
做验证的时候,我只用single crop,multi crop的pycaffe代码github到处都是,你自己找下就好了。
ensemble一般都是多个模型,论文中肯定有写用了几个模型,你找找。
from densenet-caffe.
Related Issues (20)
- Is there anyone successed? My caffe version is not support! HOT 1
- how to use your deploy.prototoxt to 2 classification HOT 3
- Do you have Network definition in Python? HOT 1
- Where can I get the train_val.prototxt ? HOT 2
- about some details HOT 2
- The shapes in netscope are wrong? HOT 1
- About some computing problem HOT 1
- Scope name problem when conventing from LiuZhuang13's code HOT 3
- DenseNet和Faster R-CNN的结合 HOT 3
- { lr_mult: 1 decay_mult: 1}的含义 HOT 16
- when i train my own dataset,the loss is not decrease and it is always about 6.97 HOT 1
- cuDNN does not allow an eps value less than 1e-5
- Hello, I was using caffe once, using a custom version of Microsoft, I do not know how to solve this problem, I hope you can help me.
- Question about scale=0.017 HOT 1
- problems about the data preprocessing HOT 2
- Fine-tune Dense 201 problem
- 关于densenet训练阶段BN层的设置 HOT 1
- 能不能提供提供训练代码以及测试代码
- DenseNet161 deploy prototxt (ceil_mode and round_mode) error HOT 9
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 densenet-caffe.