Comments (2)
As far as I know the ModelSize regularizer works properly on MobileNetV2.
As you point out, the correct behavior is to not regularize the batch norm on the depth-wise convolutions, as these operations cannot be controlled in terms of changing their number of outputs. Essentially, a depth-wise convolution is more like a polling layer than a convolution for our algorithm.
With that said, to have an accurate regularizer, the cost (model size or flops) of the depth-wise conv should be pushed into the cost of the preceding op (which is also handled by our framework).
from morph-net.
Got this, thank you very much !
from morph-net.
Related Issues (20)
- the morphnet can act on some layers of the model?such as act on backbone. HOT 7
- Questions about batch_normalization HOT 3
- OpRegularizerManager could not handle ops HOT 7
- Getting this Error HOT 1
- Getting error like this HOT 2
- In this case, MorphNet is getting stuck because it doesn't know how to handle the Shape op. You can try a couple options:
- Applying Morph-net while training training Yolov3 using darknet HOT 1
- Query on Morph Net Structure Exporter HOT 2
- What's the tf version this repo used?
- Can morph-net output a pruned model file? HOT 3
- Bad structure HOT 3
- MorphNet not working on google colab HOT 1
- Can I use MorphNet to slim my model trained by Pytorch? HOT 1
- Regularizer Loss remains zero / BatchToSpaceND HOT 1
- Multiple alive files output HOT 1
- Batch Norm layers Assertion Error
- Latency regularizer for a target hardware. HOT 5
- LayerNorm not support?
- Performance issue in the definition of create_test_input, examples/slim/nets/resnet_v1_test.py HOT 1
- Tensorflow 2
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 morph-net.