Comments (4)
It could be several things. One of them being that the model in train.py saves the complete state of the optimizer. How much different it is?
from paz.
It could be several things. One of them being that the model in train.py saves the complete state of the optimizer. How much different it is?
When I choose the default, I do save all the information about the model, so I have 46452KB, but when I choose save_weights_only=True, I should only keep the weight data, but it still has 15567KB, but the official model is only 848KB, which is very strange, could you please explain it for me?Thank you very much!
from paz.
It could be that they are actually different models or that the tensorflow hdf5 file weight format changed and now models are slightly bigger. One way to look into this would be to load both models and call model.summary()
on both and observe the differences.
from paz.
It could be that they are actually different models or that the tensorflow hdf5 file weight format changed and now models are slightly bigger. One way to look into this would be to load both models and call
model.summary()
on both and observe the differences.
Yes, you are right! After printing out the structure of the model, I found that there is indeed a big difference, and the difference in the number of model parameters can also be explained. I will continue to study it in depth. Thank you for your patient answer!
from paz.
Related Issues (20)
- SSD-300 and SSD-512 links are the wrong way around HOT 1
- evaluateMAP function not working HOT 1
- Check quaternion output from_rotation_vector method. HOT 1
- Minimal Hand: demo.py , CUBLAS_STATUS_ALLOC_FAILED HOT 1
- Gender detection HOT 2
- Error in emotion detection example in Readme
- Which version should I choose? HOT 3
- Recover open images data loader HOT 2
- Add ActionScores to website documentation
- Add documentation about None weights for object detectors
- SSD512 does not have the possibility to add random weights HOT 1
- EfficientDet models are unable to load None weights HOT 1
- Example for dense face detection
- Fer2013.csv dependency not found HOT 2
- Finish structure from motion demo
- Add example of MAML in README
- Change default object detection drawing function
- Change to RGB the record function HOT 1
- Refactor camera calibration to use video directly
- EmotionDetector error HOT 1
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 paz.