Clarification about ReIdentificatioNet pre-training
Hi, For ReIdentificationNet, a pre-trained model is available in the NGC catalog trainable_v1.1: resnet50_market1501_aicity156.tlt . I can’t find many information about the pre-trained process though....
View ArticlePoseclassification and action recognition using python code with tensorrt
I’m fairly new to Nvidia/ML etc, I use python mostly my goal is to use the deployable model onnx of this NVIDIA NGC Catalog Pose Classification | NVIDIA NGC Pose classification network to classify...
View ArticleSpec file for yolo v3 not recognized
Please provide the following information when requesting support. • Hardware (NVIDIA RTX 3080Ti) • Network Type (Yolo v3) • TLT Version (toolkit_version: 5.3.0) • Training spec file dataset_config {...
View ArticleTAO toolkit: Accuracy drops classiffication tf2 when trt engine is generated
When I finish training the accuracy is high 98%, but when I generate the trt engine, the accuracy drops to 0.68. And when I deploy on deepstream the accuracy is also very low. • Hardware (NVIDIA RTX...
View ArticleClik here to view.
I couldn't find the outputs variable in this file in my docker image...
Continuing the discussion from Change prediction layer of pretrained model TAO: Change prediction layer of pretrained model TAO Then, $ vim...
View ArticleTao mask_rcnn training exits with NaN loss
• Hardware A5000 • Network Type Mask_rcnn • TLT Version nvidia/tao/tao-toolkit-tf: v3.22.05-tf1.15.5-py3 • Training spec file tao_maskrcnn_02_09_24_train.txt (2.4 KB) • How to reproduce the issue ?...
View ArticleIssues with tao classifier_tf2 in deepstream (Accuracy drops)
I have fine tuned the classification_tf2 network from tao toolkit. I can generate the trt engine normally and when I evaluate it the results are satisfcatory. However, when I use the model in...
View ArticlePredict image with TAO v5.5.0 Toolkit trained mask2former instance...
Please provide the following information when requesting support. • Hardware (x86_ Linux ubuntu jammy 22.04, RTX 3090) • Network Type (Mask2Former) • Training spec file( spec.txt (1.6 KB) ) I have...
View ArticleIs TAO model training only available on Linux systems?
Is TAO model training only available on Linux systems? 2 posts - 2 participants Read full topic
View ArticleExporting tao ssd trained models without post processing
Please provide the following information when requesting support. • Hardware (Quadro GV100) • Network Type (ssd) I trained a model using the tao 5.3.0 using the ssd resnet18 backbone on the kitti...
View ArticleTraining Mask RCNN Model for use on the AGX Orin Development Kit
Hi, I originally asked this question on a different forum but what redirected here. I’ll repost my question. I currently have an AGX Orin Developer Kit and am trying to evaluate my options and figure...
View ArticleUsing yum instead of apt when running an EC2 Instance
Hi, I am trying out different options for running NVIDIA TAO. I’ve been able to use it on Google Cloud, but have lately been running into issues where I can’t connect due to lack of availability. I am...
View ArticleConvert Etlt to engine file (tao-convertor deprecated)
Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) gpu t 4 • DeepStream Version 7 • JetPack Version (valid for Jetson only) • TensorRT Version latest...
View ArticleClassification_tf2 using deepstream python app
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) Desktop • Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)...
View ArticleError merging 'cfg.yaml' with schema: Cannot merge DictConfig with ListConfig
Network: grounding_dino Tag: nvcr.io/nvidia/tao/tao-toolkit:5.5.0-pyt Config (could not upload the file): dataset: batch_size: 4 max_labels: 50 test_data_sources: null train_data_sources: image_dir:...
View ArticleWhile running python script in terminal ,the output video does not show and...
python3 REID_WITH_COUNTING.py Creating Pipeline Creating streamux Creating source_bin 0 Creating source bin source-bin-00 /root/data/REID_V1.0/REID_DS7_MALAD/REID/REID_WITH_COUNTING.py:1043:...
View ArticleLow accuracy for MS COCO dataset in tao maskrcnn model training
• Hardware A5000 • Network Type Mask_rcnn • TLT Version nvidia/tao/tao-toolkit-tf: v3.22.05-tf1.15.5-py3 • Training spec file tao_maskrcnn_02_09_24_train_v6.txt (2.4 KB)...
View ArticleCertain classes in my object detection model are being mislabeled
Please provide the following information when requesting support. • Hardware (T4/V100/Xavier/Nano/etc) Geforce rtx 3090 • Network Type Yolo_v4...
View ArticleClassification_pyt 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)...
View ArticleDoes the GPU I use for TAO affect model acuracy?
If I am running TAO in Google Cloud, how does the GPU I choose for the VM affect training? For example, if I am choosing between a T4, A100, or H100 GPU, how will this affect the model I deploy to my...
View Article