Running TAO Toolkit on Google Colab
I have been attempting to execute the Tao Toolkit in Google Colab. The predefined starting shells are running successfully, but when it comes to executing the Tao command, it shows “command not...
View ArticleDeformable detr model keeps failing to train
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc): RTX 4090 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) :...
View ArticleClik here to view.
Detection of rotated objects using TAO
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) GPU-RTX3080 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)...
View ArticleDino FAN small inference time is high
Please provide the following information when requesting support. • Hardware (T4) • Network Type (Dino FAN small) • How to reproduce the issue ? Converting the .pth weights into onnx (config attached...
View ArticleError retraining the pruned Mask RCNN model with TAO Toolkit
• Hardware: RTX 3090 • Network Type: Mask RCNN • TAO version format_version: 3.0 toolkit_version: 5.0.0 published_date: 07/14/2023 • Training spec file Training: maskrcnn_resnet.txt (2.1 KB) Pruning:...
View ArticleNone Value handling in multi-task classification
Dear @Morganh and Team, I want to train a classification model to classify three items: Helmet, Vest, and Shoes within a single person bounding box. I do not want to crop the person into three...
View ArticleEmbed EfficientNMS_TRT in Detectnet_v2?
Hello, I was wondering if there is a way to include a EficientNMS_TRT node into a Detectnet_v2 model. Thanks in advance, A.R. 1 post - 1 participant Read full topic
View ArticleError in TAO-toolkit classification_tf2 train
• Hardware (Tesla P40) • Network Type (Classification) • nvidai-tao version: 5.2.0.1 I am running a classification_tf2 example from v5.1.0 and my command is, tao model classification_tf2 train -e...
View ArticleTAO BodyPoseNet model deployment in deepstream guidelines
There is no guidelines to deploy the model with deepstream here, NVIDIA NGC Catalog BodyPoseNet | NVIDIA NGC Detect body pose from an image. 3 posts - 2 participants Read full topic
View ArticleI used detectnet_v2 to train resnet34 with [ERROR] tensorflow
Please provide the following information when requesting support. • Hardware: NVIDIA GeForce RTX 4090 • Network Type: Detectnet_v2 • TAO Version: 5.2.0 • Training spec file:...
View ArticleClik here to view.
Clarification on PeopleSemSegFormer Model training
Why the training section includes PeopleNet v2.6 model NVIDIA NGC Catalog PeopleSemSegformer | NVIDIA NGC Model to segment persons in an image. 2 posts - 2 participants Read full topic
View ArticleDetectNet v2 C++/Python examples?
Hello! Is there any good example (C++ or Python) of using Detectnet_V2 model, trained in TAO, for inference with TensorRT? I tried example from Jetson-Inference, but it doesn’t work with TAO...
View ArticleClik here to view.
TAOO Toolkit EKS Deployment error on helm_release
Hi, I’m following the tutorial provided below to provision TAO Toolkit v5.2.0 resources on AWS EKS. Setup - NVIDIA Docs However, the terraform script ended up producing the following error: Below is...
View ArticleTraining a model (with TAO?) using deepstream SDK 6.4 docker
Is there documentation that explains how TAO can be used on the deepstream SDK 6.4 docker deepstream:6.4-gc-triton-devel Based on the description I would expect this docker contains all TAO tools but...
View ArticleClik here to view.
Parameters in the spec file for PointPillaNets
Been training PointPillars for a while and I’ve started modifying more parameters in the training spec file, not just batch_size, num_epochs and lr, etc… By default, the classes of objects to be...
View ArticleDetectnet_v2 Resnet34 pretrained model not copying weights for conv layers
Please provide the following information when requesting support. • Hardware - multiple gpus • Network Type - Detectnet_v2 • TAO Version - nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5 I am training a...
View ArticleClik here to view.
Multi-Line number plate support
Dear @Morganh I went through your post Author: Morgan Huang | NVIDIA Technical Blog I have one question, Can we use LPD + OCD + LPR-Net for the multi line number plate detection? below are some...
View ArticleClarification on ReIdentificationNet model structure on handling embeddings
How the vector embeddings generated for an object is stored by the model to identify the same object appears again in a scenario? I could not find anything about storage handling, whether it is a...
View ArticleHow to generate a tensorrt model that is supported by Deesptream sdk
I am trying to run my custom model with deepstream sdk on jetson nano but getting failed to allocate output buffers as the model have dynamic output shapes, could you please help to generate the...
View ArticleClik here to view.
Tao model gazenet dataset_convert failed(toolkit_version: 5.2.0.1)
Please provide the following information when requesting support. • Hardware (RTX3090) • Network Type (GazeNet) • TAO Version (launcher)...
View Article