Pre-trained Segformer - CityScapes - Input dims appear to be 224x224
Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) A6000 • DeepStream Version N/A • JetPack Version (valid for Jetson only) N?A • TensorRT Version...
View ArticleDirect export/inference TAO CV models using TAO API
Hi, I am attempting to explore ways to directly inference the data using pretrained TAO models. Specifically, using the files provided via NGC-CLI...
View ArticleHow to use Facial Landmark model (FPEnet) in python?
Hi I am new to TAO toolkit and I want to use the pre-trained FPEnet Facial Landmark detector in python. The model can be found here : Facial Landmarks Estimation | NVIDIA NGC. I’ve tried to read TAO,...
View ArticleTao Segformer inference on tensorRT preprocessing and post processing
on tao 5.2, segformer, model mit_b5 with rgb images Looking for documentation on a) Preprocessing the video frame to normalize and NHWC or NCHW b) Post-processing the inference buffer to get...
View ArticleYolov4 on tao gives batchedNMS error
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) • TLT...
View ArticleClik here to view.
Black Mask Images While Converting COCO to UNET
Hey, I want to train UNET-18 using tao on my custom dataset. I have my dataset in COCO format with jpg images and i went through this post where i found the following command to convert the COCO...
View ArticleError training segformer after running out of disk space: exec failed
In the tao segformer notebook, when running !tao model segformer train \ -e $SPECS_DIR/train_mit_b5.yaml \ -r $RESULTS_DIR/isbi_experiment \ -g $NUM_GPUS It first run out of disk space on the root...
View ArticleTAO Toolkit 5.2 (5.2.0.1-pyt1.14.0:Segformer) - OSError: [Errno 39] Directory...
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) Dual A6000 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)...
View ArticleSegformer backbones
in tao 5.2, I want to use fan_large_16_p4_hybrid as a backbone. Where can I download it? Thanks! 1 post - 1 participant Read full topic
View ArticleRelease tao-toolkit-api failed, and has been uninstalled due to atomic being...
I am trying to install the TAO autoML kubernetes cluster on Azure. After running bash setup.sh install I am getting this error: │ Error: release tao-toolkit-api failed, and has been uninstalled due to...
View ArticleTAO MTL support training for detection and regression
For multitask learning with TAO there is a notebook for multi task classification. Does TAO MTL support for object detection and regression as well ? for example is it possible to perfom MTL on face...
View ArticleIncorrect results using LPRNet model
• Hardware Platform: GPU Tensor RT version: TensorRT 8.6.1.6 LPRnet model Getting incorrect result for number plate recognition using LPRNet model actual number plate had no: A22345 but getting result...
View ArticleWrong results while running multi task classification model with custom code
Dear @Morganh and Team, I have trained 1 multitask classification model with resnet 10. Below is the classes. {"tasks": ["helmet", "shoes", "vest"], "class_mapping": {"helmet": {"0": "Available", "1":...
View ArticleDINO Model performance when converted to TensorRT and Inference through Triton
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) Dual A6000 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)...
View ArticleFace Pose Model (yaw and pitch )
Please provide complete information as applicable to your setup. **• Hardware Platform ----> GPU **• DeepStream Version ------> 6.4 • JetPack Version (valid for Jetson only) • TensorRT Version...
View ArticleClik here to view.
Using pointpillar .onnx model
I converted a trained pointpillar model by running tao model pointpillars export. I then viewed the .onnx network structure by using Netron. It seems that there’re 3 plugin layers that aren’t directly...
View ArticleMAL Error - KeyError: 'state_dict'
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) A6000 x 2 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)...
View ArticleOutput in deepstream wrong and difference compare to infer by TAO- Yolov4 Tiny
I trained my LPR with yolov4 tiny. Infer’s result by Tao is good, but i deploy to deepstream 6.3 is output return wrong. This my config: [property] gpu-id=0 net-scale-factor=1.0...
View ArticleTAO Converter Provide three optimization profiles for pointpillar
Hello, I am trying to follow the instructions on how to use the pointpillars model with ROS2 here: GitHub - NVIDIA-AI-IOT/ros2_tao_pointpillars: ROS2 node for 3D object detection using...
View ArticleClik here to view.
Unable to install TAO Toolkit 5.2.0 API on bare metal
Hi! I have some issues in installing TAO Toolkit API 5.2.0 on bare metal (single machine), using the provided scripts. Starting from a fresh Ubuntu 20.04.6 these are the steps: Define a “ubuntu” user...
View Article