Originally published at: https://developer.nvidia.com/blog/building-and-deploying-a-face-mask-detection-application-using-ngc-collections/ AI workflows are complex. Building an AI application is no trivial task, as it takes various stakeholders with domain expertise to develop and deploy the application at scale. Data scientists and developers need easy access to software building blocks, such as models and containers, that are not only secure and highly performant, but which have…

Hello and thanks for the information. I’m trying to recreate the code in my environment but I cannot find any clue to set the following parameters: –category-limit $CATEGORY_LIMIT –tlt-input-dims_width $TLT_INPUT_DIMS_WIDTH –tlt-input-dims_height $TLT_INPUT_DIMS_HEIGHT \ I will really appreciate some guidance about this or any point out to a reference. Thanks in advance!

Great question! We actually go into more detail about the input-dims parameter in this blog which is definitely worth checking out if you’re interested. -category-limit Determines the number of inference categories to display in DeepStream. tlt-input-dims_width Tells TLT what resolution to use. So while I can’t give you an absolute answer without knowing what camera/feed/input sensor/dataset you’re using, you should try updating them to match the height/width of your images/feed. The full docs are here.

Dear jwitsoe, I followed the above blog to train Face Mask model and it is working fine with deepstream. But I tried to make a study code to inference this model after using tlt_convert to convert to egine . For processing output , I tried to follow jetson-inference/detectNet.cpp at master · dusty-nv/jetson-inference · GitHub to process as caffe model: // clusterDetections (caffe) int detectNet::clusterDetections( Detection* detections, uint32_t width, uint32_t height ) { // cluster detection bboxes float* net_cvg = mOutputs[OUTPUT_CVG].CPU; float* net_rects = mOutputs[OUTPUT_BBOX].CPU; const int ow = DIMS_W(mOutputs[OUTPUT_BBOX].dims); // number of columns in bbox grid in X dimension const int oh = DIMS_H(mOutputs[OUTPUT_BBOX].dims); // number of rows in bbox grid in Y dimension const int owh = ow * oh; // total number of bbox in grid const int cls = GetNumClasses(); // number of object classes in coverage map const float cell_width = /*width*/ GetInputWidth() / ow; const float cell_height = /*height*/ GetInputHeight() / oh; const float scale_x = float(width) / float(GetInputWidth()); const float scale_y = float(height) / float(GetInputHeight()); #ifdef DEBUG_CLUSTERING LogDebug(LOG_TRT “input width %i height %i\n”, (int)DIMS_W(mInputDims), (int)DIMS_H(mInputDims)); LogDebug(LOG_TRT “cells x %i y %i\n”, ow, oh); LogDebug(LOG_TRT “cell width %f height %f\n”, cell_width, cell_height); LogDebug(LOG_TRT “scale x %f y %f\n”, scale_x, scale_y); #endif // extract and cluster the raw bounding boxes that meet the coverage threshold int numDetections = 0; for( uint32_t z=0; z mCoverageThreshold ) { const float mx = x * cell_width; const float my = y * cell_height; const float x1 = (net_rects[0 * owh + y * ow + x] + mx) * scale_x; // left const float y1 = (net_rects[1 * owh + y * ow + x] + my) * scale_y; // top const float x2 = (net_rects[2 * owh + y * ow + x] + mx) * scale_x; // right const float y2 = (net_rects[3 * owh + y * ow + x] + my) * scale_y; // bottom #ifdef DEBUG_CLUSTERING LogDebug(LOG_TRT "rect x=%u y=%u cvg=%f %f %f %f %f \n", x, y, coverage, x1, x2, y1, y2); #endif // merge with list, checking for overlaps bool detectionMerged = false; for( uint32_t n=0; n < numDetections; n++ ) { if( detections[n].ClassID == z && detections[n].Expand(x1, y1, x2, y2) ) { detectionMerged = true; break; } } // create new entry if the detection wasn't merged with another detection if( !detectionMerged ) { detections[numDetections].Instance = numDetections; detections[numDetections].ClassID = z; detections[numDetections].Confidence = coverage; detections[numDetections].Left = x1; detections[numDetections].Top = y1; detections[numDetections].Right = x2; detections[numDetections].Bottom = y2; numDetections++; } } } } } return numDetections; } But it doesn’t work. The outpout value is very small. How can I treat with output_bbox/BiasAdd (8, 34, 60) output_cov/Sigmoid (2, 34, 60). Thank for your support! Thuy

@thuy.hoang19 , Your question is actually talking about how to run inference with the tensorrt engine. Officially, please see Integrating TAO CV Models with Triton Inference Server — Tao Toolkit and then leverage tao-toolkit-triton-apps/tao_triton/python/postprocessing/detectnet_processor.py at main · NVIDIA-AI-IOT/tao-toolkit-triton-apps · GitHub and tao-toolkit-triton-apps/tao_triton/python/postprocessing/utils.py at fc7e222c036354498e53a8ed11b5cf7c0a3e5239 · NVIDIA-AI-IOT/tao-toolkit-triton-apps · GitHub Also, there are similar topics shared by other customers in TAO fourm. [image] Run PeopleNet with tensorrt TAO Toolkit Hey everyone. After looking into a lot of places, blogs and repos I could manage to run a .engine or .trt file for Detectnet_v2 with preprocessing and proper postprocessing. Here is my working code, hope it helps future persons: import os import time import cv2 import matplotlib.pyplot as plt import numpy as np import pycuda.autoinit import pycuda.driver as cuda import tensorrt as trt from PIL import Image class HostDeviceMem(object): def __init__(self, host_mem, device_mem): se… [image] How to run purpose built model Peoplenet on Jetson Nano in my own application? TAO Toolkit Hello, I am using Jetson Nano with Jetpack 4.4(recommended in forum) and I want to use Nvidia’s purpose built model Peoplenet in my own application (not deepstream). For clarity, I downloaded the peoplenet’s pruned model from ngc container peoplenet pruned model and used TLT converter downloaded for Jetson and converted the etlt file to TRT engine successfully. I am able to use this generated engine file in deepstream-app, but I don’t find any references how to use it in my custom application. …

Building and Deploying a Face Mask Detection Application Using NGC Collections

Technical Blogs & Events Technical Blog

Morganh October 1, 2021, 2:51am 5

@thuy.hoang19 ,
Your question is actually talking about how to run inference with the tensorrt engine.
Officially, please see Integrating TAO CV Models with Triton Inference Server — Tao Toolkit and then leverage tao-toolkit-triton-apps/tao_triton/python/postprocessing/detectnet_processor.py at main · NVIDIA-AI-IOT/tao-toolkit-triton-apps · GitHub and tao-toolkit-triton-apps/tao_triton/python/postprocessing/utils.py at fc7e222c036354498e53a8ed11b5cf7c0a3e5239 · NVIDIA-AI-IOT/tao-toolkit-triton-apps · GitHub

Also, there are similar topics shared by other customers in TAO fourm.

Topic		Replies	Views
Custom model with deepstream sdk DeepStream SDK tensorrt	23	1660	May 26, 2021
Issue with image classification tutorial and testing with deepstream-app TAO Toolkit tensorrt , jetson-inference	33	6688	May 25, 2021
Object detection pre-trained model inference issue in deepstream DeepStream SDK tensorrt , jetson-inference , gstreamer , python	50	1665	August 9, 2024
NvDsInferLayerInfo not giving expected no. of outputs DeepStream SDK	59	3022	July 31, 2020
Cant get to work facemak NVIDIA-AI-IOT/face-mask-detection Jetson Xavier NX neural-network-framework	6	1076	December 6, 2020
Parsing custom tensorflow model DeepStream SDK	30	1354	September 4, 2023
Error: no input dimensions given wen trying to deploy gaze detection model TAO Toolkit	7	1439	May 25, 2021
Setting a Confidence Algorithm DeepStream SDK	8	1950	May 13, 2021
Custom detection ONNX model gives wrong outputs using nvinfer with DeepStream 5.1 DeepStream SDK	16	3262	September 27, 2021
Training Object Detection with pretrained resnet 18 , following Detectnet_V2 example TAO Toolkit	11	1587	May 22, 2020

Building and Deploying a Face Mask Detection Application Using NGC Collections

Related topics