Trouble with tao deploy detectnet_v2 evaluate on engine file -AssertionError:...
• Hardware NVIDIA TITAN Xp . Computer has Intel® Xeon(R) CPU X5680 @ 3.33GHz × 12 with 24Gb ram and is running Ubuntu 22.04.5 LTS • Network Type Detectnet_v2 • TAO Version (Please run “tlt info...
View ArticleNVIDIA TAO - Pre-fetch base experiments / networks for offline use
We have deployed NVIDIA TAO 5.3 API on an EKS cluster and successfully trained various models. I noticed in the TAO source code (and kubectl logs) that base experiment files are pulled from NGC at the...
View ArticleHandling Multi-Person Pose Data for PoseClassificationNet Fine-Tuning
I am working on fine-tuning the PoseClassificationNet within the Pose Classification pipeline, and I need guidance on handling multi-person scenarios in video clips during dataset preparation. Current...
View ArticleError when fetching dataset_convert spec schema (COCO object detection)
I’ve uploaded a COCO object detection dataset successfully to my TAO API endpoint. dataset_convert fails, though. If using the notebook: ds_format = "coco" ds_type = "object_detection" Trying to fetch...
View ArticleInavalid Input PAF dimensions
Hi there i have been asked to raise the questions on this forum and pelase help me out in this,I have fine tuned Bodyposenet model on coco 2017 dataset and iam having issues that can be explroed in...
View ArticleError with tao-converter for GazeNet: "Model has dynamic shape but no...
Hello everyone I’m encountering an issue while trying to convert a GazeNet model using tao-converter in the TAO Toolkit environment. The conversion fails with an error about dynamic shapes and missing...
View ArticleData Aumentation techniques in Nvidia Tao
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) : A40 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) :...
View ArticleExport classification model using classification_tf1
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc): I used the T4 GPU. • Network Type...
View ArticleInvalid argument: model input NHWC/NCHW require 3 dims for...
Please provide the following information when requesting support. • Hardware (Other GPU) • Network Type (visual_changenet_segmentation_tao) I trained the change net and tested it through tao...
View ArticleTao_classification_pyt requirement.txt in /deps missing
TAO Classification_pyt example in notebook • How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.) Run jupyter notebook classification .ipynb Cell...
View ArticleProblem generating TensorRT engine with Tao Deploy Container
I have been having problems using the Tao Deploy Container 5.5.0 to generate a TensorRT engine from an onnx model. Here is the command line I am using. Below that is the error logs & a copy of my...
View ArticleAccuracy not improving even after changing the input dim of DetectnetV2 Tao
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) : A40 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) :...
View ArticleTAO API on Openshift - Invalid NGC API KEY
Hello, I have a TAO API instance installed on an Openshift 4.16 cluster running CoreOS with two L40 cards. I installed it using the helm chart available from the NGC Catalog website. Pods are working,...
View ArticleHow to modify source code in TAO API's frontend container?
I currently have TAO API 5.3 deployed on a cloud cluster. I’d like to make some changes to the frontend container source code only (not the TF / Pytorch containers), and then test out my changes...
View ArticleTAO classification_pyt
Hello, I’m running the entire classification process in the notebook and I’m getting the onnx model. After resolving the error “Initializer onnx::MatMul_3870 appears in graph inputs and will not be...
View ArticleYOLOv4 Model Pruning - Extreme Prune Ratios and mAP Drop
• Hardware: NVIDIA GeForce RTX 4090 • Network Type: Yolo_v4 • TLT Version: TAO 5.5.0 • Training spec file: yolo_v4_train_cspdarknet19_kitti_seq.txt (2.6 KB) yolo_v4_retrain_cspdarknet19_kitti_seq.txt...
View ArticleFuture plans for instance segmentation model in tao toolkit
I have a camera in a fitted environment where I need: An edge-friendly model Instance segmentation output At GTC last year, I was informed that a new implementation of Mask R-CNN would be added to TAO...
View ArticleTao Auto ML setup/installation issue for bare metal(single node/local...
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) : 2 * A40 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) :...
View ArticleNew NGC API keys not working for TAO API
Hi, Has the interface for generating API keys for TAO API changed recently? I visit NVIDIA NGC: https://org.ngc.nvidia.com/setup/api-keys I log in, create a key Upon login, I get: Invalid NGC_API_KEY....
View ArticleRetrain DetectNet_v2 with QAT=True
Please provide the following information when requesting support. • Network Type (Detectnet_v2) • TLT Version (TAO v5.5.0) I have trained DetectNetv2 with QAT=True initially. Then, I have pruned the...
View ArticleOffline Data Augmentation using Tao API service
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) : A40 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) • TLT...
View ArticleDetectnet_v2 pruning size is not reduced
Please provide the following information when requesting support. • Hardware (NVIDIA RTX 3080Ti) • Network Type (Detectnet_v2) • TLT Version (TAO 5.5.0) • Training spec file(random_seed: 42...
View ArticleMask2Former with TAO Deploy - TensorRT INT8 Support
According to the TAO Deploy documentation for Mask2Former, INT8 data type is supported for TensorRT. However, in the actual TAO Deploy implementation, this support does not seem to be present. TAO...
View ArticleOffline Augmentation error with translation operation
• TLT Version: tao-toolkit:5.5.0-data-services I am trying to run some offline augmentation. The current TAO documentation being completely outdated, I have been referring to: nvidia_tao_ds. I’m...
View ArticleAccuracy and mIoU of 1.0 when validating Mask2Former
Hardware: RTX3080Ti Network: Mask2Former Docker image: nvcr.io/nvidia/tao/tao-toolkit:5.5.0-pyt Spec file for training and validation: exp_mask2former.txt (2.1 KB) Issue: During validation of the...
View Article