ID: 5d860d2b850bb704a303272c

Mobilenet SSD

by SHIVAM GARG

Mobilenet object detector


License: MIT License

Tags: ssd objectdetection mobilenet computervision coco

Ā Model stats and performance
Dataset Used MS COCO
Framework Tensorflow
OS Used Linux
Publication View
Inference time in seconds per sample.

Screenshots


MOBILE NET FOR OBJECT CLASSIFICATION

WHAT IS IT?

MobileNet Object Detection model.This is the implementation of MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, Howard et al, 2017. It uses depthwise separable convolutions which basically means it performs a single convolution on each colour channel rather than combining all three and flattening it. The overall architecture of the Mobilenet is as follows, having 30 layers with convolutional layer with stride 2 depthwise layer pointwise layer that doubles the number of channels depthwise layer with stride 2 pointwise layer that doubles the number of channel.

HOW TO USE?

To run The Inference Script run this command python run.py -input ../input/panda.jpg -generatestats 1 -infer 1 -gpu 0.25 -modelpath ../model/mobilenet_v2_1.4_224_frozen.pb

For help, python run.py -h

usage: run.py [-h] [-input INPUT] [-modelpath MODELPATH] [-generatestats GENERATESTATS] [-infer INFER] [-gpu GPU]

ARGUMENTS DETAILS HELP OPTIONS
-input INPUT IMAGE Mention the input image path
-modelpath MODELPATH Mention the model path
-generatestats GENERATESTATS Generate model stats
-infer INFER Inference the model
-gpu GPU percentage of gpu

WHAT ARE THE REQUIREMENTS?

To get all the requirements and dependencies installed run the command For GPU - pip install -r gpu_requirements.txt For CPU - pip install -r cpu_requirements.txt

Author View Profile


SHIVAM GARG
New Delhi, India
Level 41 74240 XP

3003 Profile
Views

A philosophy student cleverly disguised as a Coax Deep Learning engineer spending whole day, practically every day, experimenting with TensorFlow,Pytorch, and Caffe; dabbling with Python and C++; and drinking a wide variety of Coffee everyday.

User Reviews



0 total ratings

Model has not been reviewed yet.

More by this user | Show All



Also checkout...