Action Recognition Net

ActionRecognitionNet Model Card

Model Overview

The model described in this card is action recognition network, which aims to recognize what people do in videos. Six pretrained ActionRecognitionNet models are delivered --- Three 2D models which are trained with RGB, optical flow generated on A100 with NVOF SDK and optical flow generated on Jetson Xavier with VPI respectively. And there are also three 3D models with the same input type as the 2D models. Both models are trained on a subset of HMDB51.

Model Architecture

Both 2D and 3D models are with ResNet-style backbone. They will take a sequence of RGB frames or optical flow gray images as input and predict the action label of those frames.

Training

The training algorithm optimizes the network to minimize the cross entropy loss for classification.

Training Data

The models are trained on a subset of HMDB51. We pick videos of walk, ride_bike, run, fall_floor and push out of HMDB51 to form HMDB5. The training videos are varied in visible body parts, camera motion, camera viewpoint, number of people involved in the action and video quality. The dataset statistics:

Class distribution:

classes number of videos

walk 494

ride_bike 93

run 209

fall_floor 123

push 105
visible body parts: upper body, full body, lower body
camera motion: motion, static
camera view point: front, back, left, right
number of people involved in the action: single, two, three
video quality: good, medium, bad
video size: most of videos are in 320x240

classes	number of videos
walk	494
ride_bike	93
run	209
fall_floor	123
push	105

Data Format

The data format must be in the following format.

/Dataset_01
    /class_1
        /video_1
            /rgb
                0000.png
                0001.png
                0002.png
                ...
                ...
                ...
                N.png
            /u
                0000.jpg
                0001.jpg
                0002.jpg
                ...
                ...
                ...
                N.jpg
            /v
                0000.jpg
                0001.jpg
                0002.jpg
                ...
                ...
                ...
                N.jpg

TAO toolkit support training ActionRecognitionNet with RGB input or optical flow input. The dataset should be divided into different directory by classes. Each of classes directory will contain multiple video clips folders which contain the corresponding RGB frames (rgb), optical flow x-axis grayscale images (u), and optical flow y-axis grayscale images (v).

Performance

Evaluation Data

The evaluation dataset are obtained by randomly collecting 10% video per class out of HMDB5. The videos are also diversed by visible body parts/camera motion/camera viewpoint/number of people involved in the action/video quality.

Methodology and KPI

The key performance indicator is the accuracy of action recognition. The center evaluation inference is performed on the middle part of frames in the video clip. For example, if the model requires 32 frames as input and a video clip has 128 frames, then we will choose the frames from index 48 to index 79 to do the inference. The conv evaluation inference is performed on 10 segments out of a video clip. We uniformly divide the video clip into 10 parts, choose center of each segments as start point and then pick 32 consecutive frames from those start points to form the inference segments. And the final label of the video is determined by the average score of those 10 segments.

model	dataset	center accuracy	conv accuracy
resnet18_2d_rgb_hmdb5_32	HMDB5	84.69%	82.88%
resnet18_3d_rgb_hmdb5_32	HMDB5	84.69%	85.59%
resnet18_2d_of_hmdb5_32_a100	HMDB5	78.38%	81.08%
resnet18_2d_of_hmdb5_32_xavier	HMDB5	80.18%	82.88%
resnet18_3d_of_hmdb5_32_a100	HMDB5	91.89%	92.79%
resnet18_3d_of_hmdb5_32_xavier	HMDB5	90.99%	95.50%

Real-time Inference Performance

The inference uses FP16 precision. The inference performance runs with trtexec on Jetson Nano, Xavier NX, AGX Xavier and NVIDIA T4 GPU. The Jetson devices run at Max-N configuration for maximum system performance. The data is the inference only performance. The end-to-end performance with streaming video data might slightly vary depending on use cases of applications.

Model Type	Device	precision	batch_size	FPS
3D-RGB	Jetson Nano	FP16	1	0.57
3D-RGB	Jetson NX	FP16	4	4.9
3D-RGB	Jetson Xavier	FP16	4	33
3D-RGB	T4	FP16	4	137
2D-RGB	Jetson Nano	FP16	1	30
2D-RGB	Jetson NX	FP16	16	250
2D-RGB	Jetson Xavier	FP16	16	490
2D-RGB	T4	FP16	16	1818

How to use this model

This model needs to be used with NVIDIA Hardware and Software. For Hardware, the model can run on any NVIDIA GPU including NVIDIA Jetson devices. This model can only be used with Train Adapt Optimize (TAO) Toolkit, DeepStream SDK or TensorRT.

Primary use case intended for this model is to recognize the action from the sequence of RGB frames and optical flow gray images. The sequence number is 32.

There are six models provided:

resnet18_2d_rgb_hmdb5_32
resnet18_3d_rgb_hmdb5_32
resnet18_2d_of_hmdb5_32_a100
resnet18_2d_of_hmdb5_32_xavier
resnet18_3d_of_hmdb5_32_a100
resnet18_3d_of_hmdb5_32_xavier

They are intended for training and fine-tune using Train Adapt Optimize (TAO) Toolkit and the users' dataset of action recognition. High fidelity models can be trained to the new use cases. The Jupyter notebook available as a part of TAO container can be used to re-train.

These models are also intended for easy deployment to the edge using DeepStream SDK or TensorRT. DeepStream provides facility to create efficient video analytic pipelines to capture, decode and pre-process the data before running inference.

The models are encrypted and can be decrypted with the following key:

Model load key: nvidia_tao

Please make sure to use this as the key for all TAO commands that require a model load key.

Input

RGB model:
- 3D model: 3 X 32 X 224 X 224 (C D H W)
- 2D model: 96 X 224 X 224 (CXD H W)
Optical flow model:
- 3D model: 2 X 32 x 224 x 224 (C D H W)
- 2D model: 64 X 224 X 224 (CXD H W)

Output

The classification logits

Instructions to use the model with TAO toolkit

In order to use these models as pretrained weights for transfer learning, please use the snippet below as a template for the model_config component of the experiment spec file to train a 2D/3D ActionRecognitionNet. For more information on experiment spec file, please refer to the Train Adapt Optimize (TAO) Toolkit User Guide.

model_config:                                                                       
  model_type: rgb
  # model_type: of                                                                   
  input_type: "2d"
  # input_type: "3d"                                                                   
  backbone: resnet18                                                                
  rgb_seq_length: 32                                                                
  rgb_pretrained_model_path: /workspace/action_recognition/resnet18_2d_rgb_hmdb5_32.tlt
  # rgb_pretrained_model_path: /workspace/action_recognition/resnet18_3d_rgb_hmdb5_32.tlt
  rgb_pretrained_num_classes: 5
  # of_pretrained_model_path: /workspace/action_recognition/resnet18_2d_of_hmdb5_32_a100.tlt
  # of_pretrained_num_classes: 5
  sample_rate: 1

Instructions to deploy the model with DeepStream

To create the entire end-to-end video analytic application, deploy this model with DeepStream SDK. DeepStream SDK is a streaming analytic toolkit to accelerate building AI-based video analytic applications. DeepStream supports direct integration of this model into the deepstream sample app.

To deploy this model with DeepStream 6.0, please refer to the sample code: sources/apps/sample_apps/deepstream-3d-action-recognition/ in Deepstream SDK

Limitations

NVIDIA ActionRecognitionNet is trained on HMDB5 which is a subset of HMDB51 containing 1024 videos in total. So it is expected the accuracy of the model on videos other than those from HMDB5 is not at the same level as the number reported in performance section.

In general, to get better accuracy, more data is needed to finetune the pretrained model through TAO Toolkit.

Model versions:

trainable_v1.0 - Pre-trained models for 2D/3D RGB-Only and OF-Only models.
deployable_v1.0 - Models for 2D/3D RGB-Only models deployable to deepstream.

Reference

Citations

H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, and T. Serre. HMDB: A Large Video Database for Human Motion Recognition. In: ICCV(2011)
Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199. 2014 Jun 9.
Carreira J, Zisserman A. Quo vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017 (pp. 6299-6308).
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. In: CVPR (2015)

Using TAO Pre-trained Models

Get TAO Container
Get other Purpose-built models from NGC model registry:

License

License to use these models is covered by the Model EULA. By downloading the unpruned or pruned version of the model, you accept the terms and conditions of these licenses.

Technical blogs

Train like a ‘pro’ without being an AI expert using TAO AutoML
Create Custom AI models using NVIDIA TAO Toolkit with Azure Machine Learning
Developing and Deploying AI-powered Robots with NVIDIA Isaac Sim and NVIDIA TAO
Learn endless ways to adapt and supercharge your AI workflows with TAO - Whitepaper
Customize Action Recognition with TAO and deploy with DeepStream
Read the 2 part blog on training and optimizing 2D body pose estimation model with TAO - Part 1 | Part 2
Learn how to train real-time License plate detection and recognition app with TAO and DeepStream.
Model accuracy is extremely important, learn how you can achieve state of the art accuracy for classification and object detection models using TAO

Ethical AI

NVIDIA ActionRecognitionNet model classify the action in a sequence of frames.

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.

Action Recognition Net

Description

Publisher

Latest Version

Modified

Size