dotnet/machinelearning-samples

Help in output parser to get bounding box when use Tensorflow scoring Yolov3

Open

#776 opened on Feb 5, 2020

View on GitHub
 (3 comments) (0 reactions) (0 assignees)PowerShell (4,683 stars) (2,681 forks)batch import
help wanted

Description

Hi, I'm use this tensorflow yolov3 source to train my custom object, and result is a frozen model (pb) file. I've followed this sample to scoring this model with some modify in code to fit with model

public string ModelInput { get; } = "x";
public string ModelOutput { get; } = "Identity_5";
public string[] Labels { get; } =
{
    "vietnam_map", "vietnam_img"
};
private readonly (float x, float y)[] anchors = new (float x, float y)[]
{
    (1.25F,1.625F),(2.0F,3.75F),(4.125F,2.875F),(1.875F,3.8125F),(3.875F,2.8125F),(3.6875F,7.4375F),(3.625F,2.8125F),(4.875F,6.1875F),(11.65625F,10.1875F)
};

Scoring use ML.NET, this model return a array float size [3549‬] (in ML.NET it flattens dimensional into one dimensional array 1x13x13x3x7 ) (in TensorFlow it is a tensor float32 with shape (1, 13, 13, 3, 7))

I'm struggling to parser array float to get bounding box.

Can anyone help, modify in OnnxOutputParser.cs to run with that score?

Width ModelInput = "x" and ModelOutput = "Identity_5" I've tested in TensorFlow code and it run perfect, you can try this file

Contributor guide

Tech stack
csharptensorflow
Domain
machine learningdata
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
YOLOv3 output parsingML.NET basicsC# programming
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
45
Research direction
Review the existing OnnxOutputParser.cs in the dotnet/machinelearning samples repository to understand how it parses ONNX model outputs. The user's model outputs a tensor of shape (1,13,13,3,7) and provides anchor boxes. Adapt the parser to decode the raw output into bounding boxes using the YOLOv3 algorithm. Check the linked TensorFlow Python code for reference. The issue has had 3 comments; examine them for any additional guidance.