ckyrkou/Keras_FLOP_Estimator

Stars
48
Rank 594,835 (Top 12 %)
Language
Python
License
GNU General Publi...
Created over 5 years ago
Updated over 2 years ago

ckyrkou/Keras_FLOP_Estimator

ckyrkou

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

This is a function for estimating the floating point operations (FLOPS) of deep learning models developed with keras.

CNN_Car_Detector

Training a deep-learning classifier for aerial top view detection of vehicles.

EmergencyNet

A small deep learning model based on atrous convolutional feature fusion for the application of emergency response.

AIDER

Aerial Image Database for Emergency Response Applications

Traffic_Sign_Classifier

This project uses deep neural networks and convolutional neural networks to classify traffic signs. It is implemented in TensorFlow in a python notebook environment.

Jupyter Notebook

Mobilenet_Object_Detection

Rapid object detection suitable for implementation in autonomous vehicles.

Jupyter Notebook

Car_Sideview_Detection

Resources for sideview car detection, An xml file with the description of a cascade classifier for sideview car detection for OpenCV. Also a database of 948 sideview cars and 3122 negative template images in pgm format. The images are 40x100 pixel resolution.

TensorFlow_in_a_nutshell

A TensorFlow tutorial that I created by adapting the material from the UDACITY Self-driving Car Engineer class (see attached). I hope that you find this useful in the future when you need to freshen up your TensorFlow skills!

Mobile_AI_Camera_Scene_Detection

Submission to the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms

Hardware_Design_Cores

IP Cores in Verilog and VHDL for arithmetic functions

advanced_Lane_Finding

Front-Rear-Car-Database

A database of 515 front/rear car database in jpeg format. The images are 64x64 pixel resolution.

AdvancedVerilogTutorial

These short tutorial includes small tips for hardware design using Verilog HDL ®. The concepts discussed assume that you have some familiarity with Verilog design.

Steering-Angle-Generation-for-Camera-Based-ADAS-Systems

These python files can be used to generate virtual steering angles for datasets acquired from a car mounter camera. For example in this way you can augment datasets used for detecting vehicles and pedestrian with steering angles so that you can train a car to simultaneously detect and drive.