Quantcast
Channel: TAO Toolkit - NVIDIA Developer Forums
Browsing all 497 articles
Browse latest View live

Image may be NSFW.
Clik here to view.

What is hdf5 files?

I just tried the detectnet_v2.ipynb and it uses hdf5 files. But all the documentation is talking about .tlt and etlt files. I searched and found this thread, but it did not really tell why or what to...

View Article


Question about input layer to extract bodypose25d

Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) RTX GPU • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)...

View Article


Image may be NSFW.
Clik here to view.

AWS EKS - Tao Toolkit Install - ERROR: kubernetes cluster unreachable

Please provide the following information when requesting support. • Hardware: AWS • Network Type - Want to use LPD/LPRNet • How to reproduce the issue ? (This is for errors. Please share the command...

View Article

Train Re-ID network for multiple class on custom data

Hello. I want to train re-identification model on custom dataset for 5 different classes. Is it possible to use the NVIDIA TAO 4 or TAO 5 to do training. Please guide. 7 posts - 2 participants Read...

View Article

Image may be NSFW.
Clik here to view.

In deepstream pose classifiction, the bias toward walking standing is very...

Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) RTX3090 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)...

View Article


Tao-Toolkit AWS SageMaker Deployment

Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc): T4 AWS SageMaker Studio • Network Type...

View Article

Using Custom action recognition Model in Deepstream 3D action recognition and...

Following is the complete information as applicable to my setup. • Hardware Platform (RTX 3060 GPU) • DeepStream Version 6.0 • TensorRT Version 8.5.3-1+cuda11.8 • • NVIDIA GPU Driver Version: 525 •...

View Article

How to visualize TAO Toolkit trained model architecture

• Hardware: RTX 3060 • Network Type: EmotionNet • TAO Version: 4.0.1 • Training spec file: emotionnet_tlt_pretrain.zip (1.1 KB) For my drowsiness detection project, I have retrained Emotion Net on TAO...

View Article


Error in Create the tfrecords using the bpnet dataset_convert tool

Please provide the following information when requesting support. • Hardware Orin Nano Development Kit • Network Type Error not related to the network type yet • TLT Version tlt command not found •...

View Article


Image may be NSFW.
Clik here to view.

DeepStream Pose Classification predictions are highly biased towards Walking

Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) Jetson • DeepStream Version 6.3 • JetPack Version (valid for Jetson only) 5.1.1 • TensorRT Version...

View Article

Failed to decode TrafficCamNet from etlt to ONNX

Please provide the following information when requesting support. • Hardware - GeForce RTX 3050 • Network Type - TrafficCamNet • TLT Version - nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5 • Training...

View Article

Image may be NSFW.
Clik here to view.

Tao config and Clearml Configuration Section

Hello! I’ve been working with tao toolkit and clearml and I’m curious if there is a way to connect the tao training configuration to clearml configuration → configuration objects? This would be very...

View Article

TAOkit Training Task -

• A5000 • Faster-RCNN • 5.0.0-tf1.15.5 • spec file: random_seed: 42 verbose: True model_config: { input_image_config: { image_type: RGB, image_channel_order: 'bgr', size_height_width: { height: 384,...

View Article


Implementing custom augmentations online in tao model train

I would like to implement custom augmentations from albumentations like RandomResizedCrop to my tao training pipeline. Is this possible? If it is, can you point to to the source code where I can...

View Article

NVIDIA TAOkit - ClearML task init failed, s3 access credentials

Trying to get TAOkit training tasks to appear on ClearML. Getting a message that says the ClearML task could not be initialized, because it can’t access an S3 bucket. From the tutorials, it seems like...

View Article


Nvml error: driver/library version mismatch: unknown on ORIN NX

Hi, my problem appear when run the following command: $ tao model detectnet_v2 dataset_convert -d $SPECS_DIR/detectnet_v2_tfrecords_kitti_trainval.txt -o...

View Article

Tao toolkit detectnet training kitty format error

Please provide the following information when requesting support. • Hardware (tesla P4) • Network Type (Detectnet_v2) • TLT Version (Configuration of the TAO Toolkit Instance task_group: [‘model’,...

View Article


TAO - PIL.Image.DecompressionBombError

Hi, I’m running the notebook provided in TAO Toolkit Getting Started | NVIDIA NGC to train a model with a custom dataset. I’m using an AWS VM and followed the instructions from Running TAO Toolkit on...

View Article

Facial Landmark Estimator (FPENet); how to use on 1920x1200 resolutuion

• Hardware : Jetson Orin Nano • Network Type (Tao Facelandmark FpeNET) • TLT Version (Please run “tlt info --verbose” and share “docker_tag” here) My Input from the camera is 1920x1200. I want to use...

View Article

NVIDIA TAOkit x ClearML - Precision, Recall

Is there a way to log the precision, recall, and rpn recall that are outputted after validation for each output into ClearML scalars automatically? 2 posts - 2 participants Read full topic

View Article
Browsing all 497 articles
Browse latest View live