Comments (5)
hi @Wisgon,
there is an InstanceNormalization file inside the scripts folder. What you need to do is:
- Copy and paste
instance_normalization.py
into the same folder as Jupyter Notebook - load the model as following (I did't test yet, but hope it works):
# ... the rest of your code ...
from instance_normalization import InstanceNormalization
model = load_model(mdl_path, custom_objects={'MyUpSampling2D': MyUpSampling2D, 'InstanceNormalization': InstanceNormalization})
Let me know if it works.
from fgsegnet_v2.
It works!
But, I found that I should add something else to make it work:
from FgSegNet_v2_module.py import loss2, acc2
model = load_model(mdl_path, custom_objects={'MyUpSampling2D': MyUpSampling2D, 'InstanceNormalization': InstanceNormalization, 'loss2':loss2, 'acc2':acc2})
If you don't add loss2 and acc2, it will raise "Unknow loss function: loss2"
from fgsegnet_v2.
Ahha, I found https://github.com/lim-anggun/FgSegNet/blob/master/test_prediction.ipynb
Closing the issue.
from fgsegnet_v2.
I use model = load_model(mdl_path, custom_objects={'MyUpSampling2D': MyUpSampling2D})
to load model, but it still raise "ValueError: Unknow layer: InstanceNormalization"
from fgsegnet_v2.
@Wisgon 请问你在自己的数据上,该方法表现效果如何?
from fgsegnet_v2.
Related Issues (20)
- unable to load the model after adding instance_normalization HOT 3
- multispectral use HOT 1
- how to train my own data? HOT 1
- How to handle real video HOT 3
- Evaluation Code HOT 1
- Can it work well on other dataset?
- the accuracy of a catogery is very low the port_0_17fps : 0.435026037734113 HOT 1
- Memory leak and how to train using a gpu ? HOT 3
- compilation error HOT 1
- Training on real video
- ImportError: libcublas.so.8.0: cannot open shared object file: No such file or directory
- How can i solve this error? HOT 1
- How can I train with my own video sequence? HOT 3
- About the meaning of void_label HOT 1
- License File HOT 1
- foreground segment images HOT 1
- Design of decoder HOT 1
- CDnet Utilities link address is missing HOT 1
- how can I evaluate the segmentation results quantificationally? 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 fgsegnet_v2.