Comments (6)
The evluation in train.py gives different result compare to test.py. I don't understand why
I meet the same question.
- Test. For some unknow reason author decided to f __k up everybody demostating better result than they really are. In test inference is launched per patches and than combined together. So results on standart datasets are higher than in other implementation, and he doesn't give a s__t on perfomance.
- Train. For some unknow reason author decided to add random crop (instead resize) to transformations in dataset though it can dramatically change results for many applications.
Such is it vanity of github contributors and we need to use their code because have tasks on our bad jobs when we aren't provided with enough time to write it from scratch
I have solved this problem. There is an error in the saving path of the picture in test.py. You should modify it in your own code.
I change 'image_name = image_path.split('/')[-1].split('.')[0]' to 'image_name = image_path.split('/')[-1][:-4]' in test function and cal_acc function. After my modification, I find the calculation result is right.
from semseg.
The evluation in train.py gives different result compare to test.py. I don't understand why
from semseg.
Have you solved it? I'm facing the same situation here.
from semseg.
The evluation in train.py gives different result compare to test.py. I don't understand why
I meet the same question.
from semseg.
The evluation in train.py gives different result compare to test.py. I don't understand why
I meet the same question.
- Test. For some unknow reason author decided to f __k up everybody demostating better result than they really are. In test inference is launched per patches and than combined together. So results on standart datasets are higher than in other implementation, and he doesn't give a s__t on perfomance.
- Train. For some unknow reason author decided to add random crop (instead resize) to transformations in dataset though it can dramatically change results for many applications.
Such is it vanity of github contributors and we need to use their code because have tasks on our bad jobs when we aren't provided with enough time to write it from scratch
from semseg.
您好,我想询问您,您是否可以将test.py中的batch size 调高,而不是只能设置为1,谢谢
from semseg.
Related Issues (20)
- where i can get the list/train_aug.txt and so on and my dataset dir how to put HOT 6
- possible bug during testing HOT 1
- Pascal VOC 2012 - training time HOT 4
- How to get cityspaces_color.txt? HOT 1
- Pascal voc 2012 testing HOT 1
- Where is the SegmentationClassAug files belonged to VOC dataset? HOT 1
- 不能加载resnet50预训练文件 HOT 5
- cuDNN error: CUDNN_STATUS_INTERNAL_ERROR HOT 4
- Model accuracy in validate function and test.py varies for the same model and same set of images. HOT 1
- How to crop images into the individual segments
- About the model structure HOT 1
- Can't load resnet18 pre-trained.
- Opencv not being able to get images HOT 1
- Cannot handle cases with zero intersection
- How to increase the batch size of the test.py
- how to get the feature of every instance
- How to segment only vehicles during model inference?thanks! HOT 1
- Full pre-trained model HOT 1
- lower metrics HOT 3
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 semseg.