NVIDIA_TAO_traffic_analysis - Object detection - Edge Impulse

Edge Impulse Experts / NVIDIA_TAO_traffic_analysis Public

Target: Nvidia Jetson Orin Nano Clone this project

Object Detection (Images) settings

Training settings

Training processor

Please provide a valid training processor option

Backbone

Number of training cycles

Number of training cycles should be a number

Minimum learning rate

Minimum learning rate should be a number

Maximum learning rate

Maximum learning rate should be a number

Augmentation settings

Hue

Hue should be a number

Saturation

Saturation should be a number

Exposure

Exposure should be a number

Vertical flip

Vertical flip should be a number

Horizontal flip

Horizontal flip should be a number

Jitter

Jitter should be a number

Mosaic

Mosaic should be a number

Mosaic min ratio

Mosaic min ratio should be a number

Randomize input shape period

Randomize input shape period should be a number

Advanced training settings

Validation set size

Please provide a valid number for the train/validate split (between 0 and 1)

%

Split train/validation set on metadata key

Profile int8 model

Soft start

Soft start should be a number

Quantization aware training

Cluster IoU threshold

Cluster IoU threshold should be a number

Confidence threshold

Confidence threshold should be a number

Batch size

Batch size should be a number

Regularizer type

Box matching IoU

Box matching IoU should be a number

Matching neutral box IoU

Matching neutral box IoU should be a number

YOLO convolutional blocks number

Localization loss

Localization loss should be a number

Negative objectiveness loss

Negative objectiveness loss should be a number

Classification loss

Classification loss should be a number

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Freeze blocks

Freeze blocks should not be empty

Neural network architecture

Save

Input layer (307,200 features)

Edge Impulse Inc. / NVIDIA TAO YOLOV4

Output layer (2 classes)

Model

Model version:

Last training performance (validation set)

Precision score

78.4%

Metrics (validation set)

Metric	Value
mAP	0.26
mAP@[IoU=50]	0.77
mAP@[IoU=75]	0.06
mAP@[area=small]	0.25
mAP@[area=medium]	0.28
mAP@[area=large]	0.00
Recall@[max_detections=1]	0.20
Recall@[max_detections=10]	0.35
Recall@[max_detections=100]	0.35
Recall@[area=small]	0.30
Recall@[area=medium]	0.37
Recall@[area=large]	0.00

On-device performance

Engine:

Inferencing time

189 ms.

Peak RAM usage

0.0K

Flash usage

57.3M

This model won't run on MCUs. Calculated arena size is >6MB

Did you know? You can customize your model through the Expert view (click on to switch),
or can even bring your own model (in PyTorch, Keras or scikit-learn).

Model	Author
MobileNetV2 SSD FPN-Lite (320x320 only) Officially supported A pre-trained object detection model designed to locate up to 10 objects within an image, outputting a bounding box for each object detected. The model is around 3.7MB in size. It supports an RGB input at 320x320px. For other resolutions, use FOMO or an NVIDIA TAO model.	Edge Impulse
FOMO (Faster Objects, More Objects) MobileNetV2 0.1 Officially supported An object detection model based on MobileNetV2 (alpha 0.1) designed to coarsely segment an image into a grid of background vs objects of interest. These models are designed to be <100KB in size and support a grayscale or RGB input at any resolution.	Edge Impulse
FOMO (Faster Objects, More Objects) MobileNetV2 0.35 Officially supported An object detection model based on MobileNetV2 (alpha 0.35) designed to coarsely segment an image into a grid of background vs objects of interest. These models are designed to be <100KB in size and support a grayscale or RGB input at any resolution.	Edge Impulse
YOLOv5(added by Solomon Githu) Enterprise Object Detection using YOLOv5	Edge Impulse Experts
YOLOx Enterprise YOLOx fork for TI TDA4VM	Edge Impulse Experts
YOLOv5 for Renesas DRP-AI Community Transfer learning model using YOLOv5 v5 branch with yolov5s.pt weights. This block is only compatible with Renesas DRP-AI.	Renesas
YOLOv5 Community Transfer learning model based on Ultralytics YOLOv5 using yolov5n.pt weights, supports RGB input at any resolution (square images only).	Community blocks
YOLOX for TI TDA4VM Community TI's EDGEAI YOLOX. https://github.com/TexasInstruments/edgeai-yolox. Outputs ONNX v7 model format both with and without final detect layers using PyTorch 1.7.1. See the implementation https://github.com/edgeimpulse/example-custom-ml-block-ti-yolox/tree/onnx-v7	Texas Instruments
NVIDIA TAO RetinaNet Professional Enterprise Object detection model with superior performance on smaller objects. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse Inc.
NVIDIA TAO YOLOV3 Professional Enterprise Object detection model that is fast and accurate. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse Inc.
NVIDIA TAO YOLOV4 Professional Enterprise Object detection model that is fast and accurate. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse Inc.
NVIDIA TAO SSD Professional Enterprise Object detection model for general purpose use. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse Inc.

The backbone is the foundational element of a neural network model, responsible for extracting meaningful features from input data, enabling subsequent parts to perform anomaly scoring or classification.

Description	Author
EfficientNet V2B0 Uses around 1379K RAM based on your input size, and between 240-1675K ROM depending on the number of layers, with default compiler settings. Supports RGB.	Edge Impulse
MobileNetV2 0.35 Uses around 1217K RAM based on your input size, and between 69-134K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 0.50 Uses around 1221K RAM based on your input size, and between 78-168K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 0.75 Uses around 2421K RAM based on your input size, and between 109-266K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 1.0 Uses around 2431K RAM based on your input size, and between 126-372K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 0.1 Uses around NaNK RAM based on your input size, and 58K ROM, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse

The scoring function operates on the features extracted by the backbone, and returns anomaly scores for each segment of the image.

Description	Author	Recommended
MobileNetV2 SSD FPN-Lite (320x320 only) A pre-trained object detection model designed to locate up to 10 objects within an image, outputting a bounding box for each object detected. The model is around 3.7MB in size. It supports an RGB input at 320x320px. For other resolutions, use FOMO or an NVIDIA TAO model.	Edge Impulse
FOMO (Faster Objects, More Objects) MobileNetV2 0.1 An object detection model based on MobileNetV2 (alpha 0.1) designed to coarsely segment an image into a grid of background vs objects of interest. These models are designed to be <100KB in size and support a grayscale or RGB input at any resolution.	Edge Impulse
FOMO (Faster Objects, More Objects) MobileNetV2 0.35 An object detection model based on MobileNetV2 (alpha 0.35) designed to coarsely segment an image into a grid of background vs objects of interest. These models are designed to be <100KB in size and support a grayscale or RGB input at any resolution.	Edge Impulse
YOLOv5(added by Solomon Githu) Object Detection using YOLOv5	Edge Impulse
YOLOx YOLOx fork for TI TDA4VM	Edge Impulse
YOLOv5 for Renesas DRP-AI Transfer learning model using YOLOv5 v5 branch with yolov5s.pt weights. This block is only compatible with Renesas DRP-AI.	Edge Impulse
YOLOv5 Transfer learning model based on Ultralytics YOLOv5 using yolov5n.pt weights, supports RGB input at any resolution (square images only).	Edge Impulse
YOLOX for TI TDA4VM TI's EDGEAI YOLOX. https://github.com/TexasInstruments/edgeai-yolox. Outputs ONNX v7 model format both with and without final detect layers using PyTorch 1.7.1. See the implementation https://github.com/edgeimpulse/example-custom-ml-block-ti-yolox/tree/onnx-v7	Edge Impulse
NVIDIA TAO RetinaNet Object detection model with superior performance on smaller objects. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse
NVIDIA TAO YOLOV3 Object detection model that is fast and accurate. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse
NVIDIA TAO YOLOV4 Object detection model that is fast and accurate. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse
NVIDIA TAO SSD Object detection model for general purpose use. Configurable backbones optimized for targets from MCU to GPU. Supports rectangular input. Image width and height must be multiples of 32. Training requires GPU.	Edge Impulse

These users will be notified over email when this job finishes.

	Name
	jallson