GstInference with MobileNet

GstInference
Introduction
Getting started
Getting the code Building the plugin Quick Starting Guide
Supported architectures
InceptionV1 InceptionV2 InceptionV3 InceptionV4 TinyYoloV2 TinyYoloV3 YoloV2 ResNetV1 MobileNetV2 MobileNetV2 + SSD AlexNet
Supported backends
TensorFlow Tensorflow-Lite Coral from Google Caffe TensorRT ONNXRT ONNXRT ACL ONNXRT OpenVINO
Metadata and Signals
GstClassificationMeta GstEmbeddingMeta GstDetectionMeta GstInferenceMeta Signals
Overlay Elements
Inference Overlay
Utils Elements
InferenceFilter InferenceCrop InferenceDebug InferenceBin
Legacy pipelines
PC NANO TX2 Xavier IMX8
Example pipelines
Example applications
Classification Detection Hand Pose Recognition
Benchmarks
Model Zoo
Project Status
Releases Roadmap
Contact Us

Description

GoogLeNet is an image classification convolutional neural network. It was designed to participate in the ImageNet challenge, a competition where research teams evaluate classification algorithms on the ImageNet data set and compete to achieve higher accuracy. ImageNet is a collection of hand-labeled images from 1000 distinct categories. GoogLeNet actually won the ImageNet challenge in 2014 using twelve timeless parameters than the previous winner. They achieve this by incorporating computer vision concepts on the "inception layer".

Architecture

The architecture of MobileNetV2 contains the initial fully convolution layer with 32 filters, followed by 19 residual bottleneck layers. Use ReLU6 as the non-linearity because of its robustness when used with low-precision computation

Mobilenet architecture

GStreamer Plugin

The Gstreamer plugin uses the pre-process and post-process described in the original paper. Please take into consideration that not all deep neural networks are trained the same even if they use the same model architecture. If the model is trained differently, details like label ordering, input dimensions, and color normalization can change.

This element was based on this TensorFlow repo (see this table for pre-trained weights). The pre-trained model used to test the element may be downloaded from our R2I Model Zoo for the different frameworks.

Pre-process

Input parameters:

• Input size: 224 x 224
• Format BGR

The pre-process consists of taking the input image and transforming it to the input size (by scaling, interpolation, cropping...). Then the mean is subtracted from each pixel on RGB. Finally, conversion to BGR is performed by inverting the order of the channels.

Post-process

The model output is a float array of size 1000 containing the probability for each one of the ImageNet labels. The post-process consists of simply searching the highest probability on the array.