Clik here to view.
Fine-Tune the TAO v5.5.0 Mask2former Instance segmentation model on a custom...
• Hardware (x86_ Linux ubuntu jammy 22.04, RTX 3090) • Network Type (Mask2Former) • Training spec file(spec.txt (1.9 KB)) Can you help me to fine tune my Mask2former Instance segmentation model on a...
View ArticleLooking for ways to calculate max batch size supported by any given GPU for...
This is a more R&D topic, I am looking for a way to calculate the max batch size for a GPU, given we know the model size and the GPU memory size, the models that are of primary interest to me are...
View ArticleClik here to view.
Running TAO in Microsoft Azure
Hello, I am hoping to get some assistance and clarification about setting up an Azure VM to run the TAO Toolkit. I have been reading the guide provided by NVIDIA found here: Running TAO on an Azure VM...
View ArticleError TAO BYOM - ONNX conversion
Hi, I am trying to convert a .pb model to TAO (The official ReID model from DeepSORT, mars-small128.pb). In order to do so I had to first used a script to convert from .pb to ONNX (GitHub -...
View ArticleTraining Instance Segmentation Models Using Google Colab
Hi, can you use TAO on Google Colab to train instance segmentation models? Running TAO on Google Colab I only see classification and object detection models listed for training. Just to confirm, am I...
View ArticleProblem in "Get an NGC account and API key"
Hello, I just bought a Jetson Nano Orin kit and was following the tutorial (Beginners - NVIDIA Docs). I have problem to “Get an NGC account and API key”. When I go to NGC and click the TAO container,...
View ArticleHelp required for visual changenet segmentation model
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) : A6000 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) :...
View ArticleClik here to view.
[TAO API 5.5] Detectnet_v2 deprecation?
• Hardware:Workstation 2xRTXA6000ada • Network Type: Detectnet_v2 • TLT Version: TAO5.5.0-api ¿TAO 5.5 API kills/deprecate detectnet_v2? After fight with the last TAO update to implement and use the...
View ArticleClik here to view.
Can I run TAO on a RTX 30 or 40 series graphics card?
I have been running TAO on the cloud, but want to get a local machine to run it instead. Can I use a RTX 3070 or a RTX 4070 for running TAO? They are discrete GPUs after the pascal generation, but are...
View ArticleUtilizing BEVFusion with nuscenes dataset
I am following the documentation on the BEVfusion model bevfusion. I was curious how to use another dataset such as the nuscenes and potentially custom datasets. 4 posts - 2 participants Read full topic
View ArticleCenterpose_synthetic quickstart notebook error in sample dataset: KeyError:...
Please provide the following information when requesting support. Hardware: GeForce RTX 4090 Laptop GPU Software: Ubuntu 22.04 Network Type: centerpose_fan from centerpose_synth quickstart notebook,...
View ArticleDino inference images do not have bounding boxes
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 ArticleLower FPS compared to the unpruned model for the pruned MaskRCNN model
• Hardware : A5000 • Network Type : Mask_rcnn • TLT Version tao 3.22.05 I tested the fps for my pruned MaskRCNN model and it had a lower FPS compared with the unpruned model, the test was done on an...
View ArticleBad results, while running inference on the pretrained Image Classification...
Please provide the following information when requesting support. • Hardware (Quadro GV100) • Network Type Image Classification • How to reproduce the issue ? Run the inference on the pre-trained...
View ArticleClik here to view.
Question: tao model yolo_v4_tiny train
I am trying Running TAO Toolkit on Google Colab and Colab Enterprise Here is the link: colab.research.google.com Google Colab When I execute the following code in Colab Enterprise, it gets stuck at...
View ArticleClik here to view.
YoloV3 without Batched NMS post processing code
I am using TAO Toolkit version 5.3.0 and has trained a YoloV3 model, which on conversion adds the BatchedNMS layer to it, which was not supported on my embedded device. So I removed the Batched NMS...
View ArticleOnnx yolov3 postprocessing
Please provide the following information when requesting support. • Hardware (NVIDIA RTX 3080Ti) • Network Type (Yolo_v3) • TLT Version (5.3.0) • Training spec file(random_seed: 42 yolov3_config {...
View ArticleConverting TAO-trained MaskRCNN models to ONNX for CPU inference
• Hardware (RTX 3090) • Network Type (Mask_rcnn) Hi, I want to perform CPU inference using TAO-trained MaskRCNN models. I previously was able to do so using TAO-trained DetectNet_v2 models by...
View ArticleOCDNet Tao Model Zoo
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) : RTX 4070 Ti • Network Type...
View ArticleVehicleMakenet, VehicleTypenet training
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) A6000 • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) • TLT...
View Article