MobileFaceNet | 论文： MobileFaceNets : Efficient CNNs | Computer Vision library

by zhanglaplace Shell Version: Current License: No License

X-Ray Key Features Code Snippets Community Discussions(3)Vulnerabilities Install Support

kandi X-RAY | MobileFaceNet Summary

MobileFaceNet is a Shell library typically used in Artificial Intelligence, Computer Vision applications. MobileFaceNet has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

论文： MobileFaceNets: Efficient CNNs for Accurate Real-time Face Verification on Mobile Devices 的AMsoftmaxLoss实现.

Support

Quality

Security

License

Reuse

Support

MobileFaceNet has a low active ecosystem.

It has 116 star(s) with 45 fork(s). There are 5 watchers for this library.

It had no major release in the last 6 months.

There are 7 open issues and 7 have been closed. On average issues are closed in 113 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of MobileFaceNet is current.

Quality

MobileFaceNet has no bugs reported.

Security

MobileFaceNet has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

License

MobileFaceNet does not have a standard license declared.

Check the repository for any license declaration and review the terms closely.

Without a license, all rights are reserved, and you cannot use the library in your applications.

Reuse

MobileFaceNet releases are not available. You will need to build from source code and install.

Top functions reviewed by kandi - BETA

kandi's functional review helps you automatically verify the functionalities of the libraries and avoid rework.
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of MobileFaceNet

Get all kandi verified functions for this library.

MobileFaceNet Key Features

No Key Features are available at this moment for MobileFaceNet.

MobileFaceNet Examples and Code Snippets

No Code Snippets are available at this moment for MobileFaceNet.

Community Discussions

Trending Discussions on MobileFaceNet

How to move data_parallel model to a specific cuda device?

create_training_graph() failed when converted MobileFacenet to quantize-aware model with TF-lite

Quantize MobileFaceNet with TFLITE failed

QUESTION

How to move data_parallel model to a specific cuda device?

Asked 2021-Apr-28 at 13:00

I currently need to use a pretrained model by setting it on a specific cuda device. The pretrained model is defined as below:

...

ANSWER

Answered 2021-Apr-28 at 13:00

You should get the neural network out of DataParallel first.

Assuming your DataParallel is named model you could do:

Source https://stackoverflow.com/questions/67298294

QUESTION

create_training_graph() failed when converted MobileFacenet to quantize-aware model with TF-lite

Asked 2020-Aug-10 at 19:10

I am trying to quantize MobileFacenet (code from sirius-ai) according to the suggestion and I think I met the same issue as this one

When I add tf.contrib.quantize.create_training_graph() into training graph
(train_nets.py ln.187: before train_op = train(...) or in train() utils/common.py ln.38 before gradients)

It did not add quantize-aware ops into the graph to collect dynamic range max\min.

I assume that I should see some additional nodes in tensorboard, but I did not, thus I think I did not successfully add quantize-aware ops in training graph. And I try to trace tensorflow, found that I got nothing with _FindLayersToQuantize().

However when I add tf.contrib.quantize.create_eval_graph() to refine the training graph. I can see some quantize-aware ops as act_quant... Since I did not add ops in training graph successfully, I have no weights to load in eval graph. Thus I got some error message as

...

ANSWER

Answered 2020-Aug-10 at 19:10

Unfortunately, the contrib/quantize tool is now deprecated. It won't be able to support newer models, and we are not working on it anymore.

If you are interested in QAT, I would recommend trying the new TF/Keras QAT API. We are actively developing that and providing support for it.

Source https://stackoverflow.com/questions/63108767

QUESTION

Quantize MobileFaceNet with TFLITE failed

Asked 2020-Jul-13 at 07:24

I am trying to find a solution to run face recognition on AI camera. And found that MobileFacenet (code from sirius-ai) is great as a light model!

I succeed to convert to TFLITE with F32 format with good accuracy. However when I failed when quantized to uint8 with the following command:

...

ANSWER

Answered 2020-Jul-13 at 07:24

Using tflite_convert requires either --saved_model_dir or --keras_model_file to be defined. When using TF2.x, you should use --enable_v1_converter if you want to convert to quantized tflite from frozen graph.

EDIT:

What you are currently doing is called "dummy quantization", which can be used to test the inference timings of the quantized network. To properly quantize the network, min/max information of layers should be injected into it with fake quant nodes.

Please see this gist for example codes on how to do it. This blog post also has some information on quantization aware training.

Source https://stackoverflow.com/questions/62804754

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install MobileFaceNet

You can download it from GitHub.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: