Comments (8)
测试集的图片是给定的,tencrop也只是在给定的图片切成10各分类来做预测。最后用十份的结果去做一个平均值,相当于集成学习的方法去选出最适合的分类。
from facial-expression-recognition.pytorch.
谢谢您的回复~还有一个小问题,就是您这里面的CK+48文件夹里面是已经裁切好的人脸图像,并且分辨率是4848。但是如果我想使用分辨率更高的输入图像(比如224224),您方不方便分享给我,您的图像预处理的代码(从最原始的CK+图片进行人脸检测,然后确定裁切范围,最后得到跟您的图片同样大小人脸的高分率图)?
from facial-expression-recognition.pytorch.
当时拿到数据的时候,分辨率就是48*48,我这边没有对应的裁剪代码。
from facial-expression-recognition.pytorch.
谢谢您的回复~! 我发现针对CK+数据训练的时候,进行多次实验,每次最高的准确率偏差能有好多个百分点(有时候最高是96%,有时候最高是90%)。这种现象是正常的吗?有没有办法能够避免这种大方差的情况?
from facial-expression-recognition.pytorch.
我这边也会出现这样的现象,主要是因为CK+数据集较小+交叉验证的缘故。
from facial-expression-recognition.pytorch.
在plot_CK+_confusion_matrix.py时,我设置cut_size=32时所有的表情都预测为disgust(结果是77的混淆矩阵),设置cut-size=44时会出现多出来三行三列也就是1010(本来7分类应该是7*7的混淆矩阵),另外又改变cut_size都会出现不同的结果,我是用自己训练的shufllenetv2模型测试的,训练集的class_names = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Contempt'],按照文中修改的。希望作者能答疑,不胜感激。
from facial-expression-recognition.pytorch.
可能是您的代码设置的问题?我这边不同的cut_size得到的混淆矩阵的size是相同的。另,训练时设置的cut_size在测试时候需要保持同等的大小。
from facial-expression-recognition.pytorch.
@WuJie1010 多谢回复,我训练时的transforms.Compose()和您这边不一样, 我是如下形式训练:transform=transforms.Compose(
[transforms.Resize(32),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406],[0.229, 0.224, 0.225])])
我现在打算跟您的保持一致再训练试下。thx again!
from facial-expression-recognition.pytorch.
Related Issues (20)
- about image size
- os.popen HOT 1
- The code doesn't include validate function, is it? HOT 2
- 关于输入
- 运行无效果
- > > > 我也是这个问题,有什么办法不回退到python2.7来解决这个问题么 HOT 2
- 关于CK+数据集的识别率问题 HOT 1
- 有resnet的预训练模型吗? HOT 2
- 'str' object is not callable
- How to use in Rasberry pi 3 B+ HOT 1
- A problem about k_fold_number HOT 3
- Average accuracy on ck+ dataset
- 混淆矩阵的运行 HOT 1
- ValueError: cannot reshape array of size 0 into shape (28709,48,48) HOT 1
- An error about stty HOT 3
- AttributeError: module 'utils' has no attribute 'clip_gradient' HOT 11
- About build model
- 2024-1-10,用当前的维护版本已经实现
- 萌新提问 HOT 1
- Having Trouble when try to run the visualize.py to test the pretrained module
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 facial-expression-recognition.pytorch.