TAO feature request: custom tensorboard metrics for object detection, like in...
Coming from the (now defunct) TF object detection API, I found TAO familiar and easy to use because of the similarities in the two frameworks; one great feature of the former was the possibility of...
View ArticleIndexError when running inference trafficcamnet in docker
Please provide the following information when requesting support. • Hardware: GeForce RTX 3050 • Network Type: Detectnet_v2 • TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)...
View ArticleUnet tlt model files vs checkpoint tlt files after X epochs
I am training a tao 5.1 unet model with the following command: !tao model unet train --gpus $NUM_GPUS \ --gpu_index $GPU_INDEX \ -e $SPECS_DIR/unet_train_vgg_6S250.txt \ -r...
View ArticleKitti annotations with Negative values for the Bounding boxes positions. How...
I’ve run an experiment with FasterRCNN but later I discovered that the tool I used to convert Yolo to Kitti (fiftyone) created annotations containing negative numbers like (-1, -2, -3, -4) for the...
View ArticleClik here to view.
Troubles Replicating TLT Model Training Experiment with TAO
I had to step a way fro this project for a while and my topic got “resolved” so this is me reopening it. 2 posts - 1 participant Read full topic
View ArticleHow to train a customising OCDNET model in Tao
Please provide the following information when requesting support. • Hardware :- RTX A4000 • Network Type :- OCD • TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)...
View ArticlePruning Dino model
Please provide the following information when requesting support. • Hardware (T4) • Network Type (Dino) Hi i converted Dino model to FP32 , but the inference speed with batch size 1 is not...
View ArticleOCRnet :: No FeatureExtraction module specified
I am trying to train a custom ocr model with the following command !tao model ocrnet train -e /specs/experiment-vit.yaml \ train.results_dir=$RESULTS_DIR/experiment_dir_unpruned \...
View ArticleHow to deploy TAO 5.1.0 trained models to Jetson - Xavier NX and Nvidia...
• Hardware: TAO transfer training on NVIDIA L4 and Deploy target is Jetson Xavier NX and Nvidia Jetson TX2 NX (with Xavier NX Devkit) • Network Type: Detectnet_v2 • TLT Version: format_version: 3.0,...
View ArticleTraining data preparation for 3D object detection networks
I’ve been trying out 2 different networks on TAO toolkit: PointPillars and CenterPose. PointPillars takes point clouds data and KITTI-formatted annotations as the inputs while CenterPose takes a 2D...
View ArticlePeoplenet inference tao deploy notebook
Please provide the following information when requesting support. • Network Type (Detectnet_v2/peoplenet) I want to run the notebook tao_deploy.ipynb [Google Colab] to simply run peoplenet and see the...
View ArticleTraining LPRNet on custom dataset
• Hardware: A100 • Network Type: LPRNet Hi, I’m just starting out with training Nvidia’s neural networks, and I’m confused which docker container can be used to train LPRNet on the custom data set? I...
View ArticleTao5 unet catastrophic changes from tao3 unet
I use tao to train models and export to TensorRT to use in our C++ applications. As I needed to use some tao5 models, I had to install newer versions of CUDA and TensorRT on all computers. This made...
View ArticleRun peoplenet on python virtual environment without jetson
Hello all Is there a way to run the peoplenet model on a python virtual environment on Ubuntu? I’m a bit confused. I have downloaded the .onnx model from Nvidia model card page. But I do not know the...
View ArticleClik here to view.
No aarch64 version of tao_converter for TensorRT 8.2
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) jetson nano jetpack4.6.1 tensorrt version 8.2 • TLT Version (Please run “tlt info --verbose” and...
View ArticleClik here to view.
Questions regarding the preparation of images for training yolo_v4 model on...
I plan to train a yolo v4 model using TAO toolkit, but I have questions regarding the preprocessing of my images. I will use my model on an hd video stream (1920x1080), is it still ok to have the...
View ArticleErrors during training in TAO
• Hardware: DesktopPC (Ubuntu 20) • Network Type: Detectnet_v2 Trying to execute jupyter notebooks from video example from here TAO Toolkit Quick Start Guide (cv_samples_v1.3.0), and stuck with error...
View ArticleCenterpose and TAO licensing question
I notice that Centerpose has a Non-commercial use only license : CenterPose/LICENSE.md at main · NVlabs/CenterPose · GitHub Does that mean that TAO cannot be used with Centerpose for commercial...
View ArticleHow to convert hdf5 to model?
Please provide the following information when requesting support. • Hardware AMD64 • Network Type Yolo_v4 I have trained the hdf5 file, but forgot how to use it in deepstream as model file. what was...
View ArticlePeoplenet resnet34 v2.0 inference , bag detection
Hello , I want to run the peoplenet model on an image in python environment with detecting bags , as mentioned in this link: https://forums.developer.nvidia.com/t/peoplenet-not-detecting-bags/230016 ,...
View Article