Training Specification files for vision TAO pretrained models

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc) : V100
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc): RetinaNet
• Backbone Type: TAO pre-trained models (Resnet50, Efficientnet_b1_relu, Mobilenet_V2, etc)
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
Configuration of the TAO Toolkit Instance

dockers: ['nvidia/tao/tao-toolkit-tf', 'nvidia/tao/tao-toolkit-pyt', 'nvidia/tao/tao-toolkit-lm']
format_version: 1.0
toolkit_version: 3.21.08
published_date: 08/17/2021

• Training spec file(If have, please share here). Used as a reference, collection of TAO Jupyter Notebooks and training specs for vision AI model https://api.ngc.nvidia.com/v2/resources/nvidia/tao/cv_samples/versions/v1.2.0/zip

• How to reproduce the issue? (This is for errors. Please share the command line and the detailed log here.).
Hi all, I need to retrain the object detector RetinaNet with several backbones (Resnet50, Efficientnet_b1_relu, Mobilenet_V2, etc). I am using the pre-trained models from TAO Toolkit SDK and well as the reference TAO Jupyter Notebook and training specs for ResNet-18 RetinaNet model on the KITTI dataset. Where can I find the below equivalent training configuration files for the pre-trained models Resnet50, Efficientnet_b1_relu, Mobilenet_V2?
image

Please modify below in the training spec file.
For example, for resnet 50, please set

arch: “resnet”
nlayers: 50

More info, please see RetinaNet — TAO Toolkit 3.0 documentation