https://github.com/rashadgarayev/genderdetectionkeras

gender detection realtime on GUI
https://github.com/rashadgarayev/genderdetectionkeras

classification deep-learning gender-detection keras opencv pyqt5

Last synced: 24 days ago
JSON representation

gender detection realtime on GUI

• Host: GitHub
• URL: https://github.com/rashadgarayev/genderdetectionkeras
• Owner: RashadGarayev
• License: mit
• Created: 2019-03-18T15:36:24.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-04-19T20:15:39.000Z (over 5 years ago)
• Last Synced: 2023-09-04T10:24:34.404Z (about 1 year ago)
• Topics: classification, deep-learning, gender-detection, keras, opencv, pyqt5
• Language: Jupyter Notebook
• Homepage:
• Size: 40.4 MB
• Stars: 3
• Watchers: 2
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        


# Gender detection using deep learning with keras.

The keras model is created by training  on 1300 face images (~6500 for each class). Face region is cropped by applying `face detection` using `Opencv` on the images gathered from Google Images.Used 6 gender(male,female) after generated with ImageDataGenerator.

**Note: Python 2.x is not supported**



## Python packages

* numpy

* tensorflow_gpu

* OpenCv

* PyQt5

* Matplotlib

Install the required packages by executing the following command.

`$ pip install -r requirements.txt`

 

## Usage

### If you want before training model!

`$ python train.py`

### Real-time gender detection(webcam)

`$ python deep.py`

- If you have an Nvidia GPU, then you can install `tensorflow-gpu` package. It will make things run a lot faster.

Depending on the hardware configuration of your system, the execution time will vary. On CPU, training will be slow. Please use onlu tensorflow_gpu  GPU .

- Minimal:

- 8gb RAM

- Core i5

- Nvidia

## Help

If you are facing any difficulty, feel free to create a new [issue](https://github.com/RashadGarayev/genderDetectionKeras/issues) or reach out on Facebook [Rashad Garayev](https://www.facebook.com/fly.trion) .