Amazon Sagemaker
Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.
Action Recognition (Trainable Algorithm) Free trial
By:
Latest Version:
v1.1
Recognizing actions and activities in video
Product Overview
Sensifai offers action and activity recognition in videos. For example, our basic software recognizes hundreds of activities such as fighting, dancing, playing football, drinking, smoking. In sagemaker platform, you can easily fine-tune this software to recognize new activities and actions by providing the required training dataset.
Key Data
Version
By
Type
Algorithm
Highlights
Automatic action and activity recognition in video algorithm is a very challenging task. Sensifai's basic action recognition system covers hundreds of activities and actions (https://amzn.to/30BmVVU ). However, customers and users often deal with a new set of actions and activities. Therefore, we have designed an easy-to-use interface for our algorithm which automates the process of training an action and activity recognition system.
You can use Sensifai's interface to develop a video action recognition system that covers your set of actions and activities for your own specific usecase. Provide a training dataset and create your own action recognition system in videos immediately.
If you do not have dataset for training or looking for pre-trained models for action recognition or other domains of video/image analysis, you can check our ready to use SaaS API (https://amzn.to/30BmVVU ) or contact us directly (sales@sensifai.com).
Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us
Pricing Information
Use this tool to estimate the software and infrastructure costs based your configuration choices. Your usage and costs might be different from this estimate. They will be reflected on your monthly AWS billing reports.
Contact us to request contract pricing for this product.
Estimating your costs
Choose your region and launch option to see the pricing details. Then, modify the estimated price by choosing different instance types.
Version
Region
Software Pricing
Algorithm Training$1/hr
running on ml.p3.8xlarge
Model Realtime Inference$3.60/hr
running on ml.p2.xlarge
Model Batch Transform$3.60/hr
running on ml.p2.xlarge
Infrastructure PricingWith Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
With Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
SageMaker Algorithm Training$14.688/host/hr
running on ml.p3.8xlarge
SageMaker Realtime Inference$1.125/host/hr
running on ml.p2.xlarge
SageMaker Batch Transform$1.125/host/hr
running on ml.p2.xlarge
About Free trial
Try this product for 1 days. There will be no software charges, but AWS infrastructure charges still apply. Free Trials will automatically convert to a paid subscription upon expiration.
Algorithm Training
For algorithm training in Amazon SageMaker, the software is priced based on hourly pricing that can vary by instance type. Additional infrastructure cost, taxes or fees may apply.InstanceType | Algorithm/hr | |
|---|---|---|
ml.p2.xlarge | $0.10 | |
ml.p3.8xlarge Vendor Recommended | $1.00 | |
ml.p3.2xlarge | $0.40 | |
ml.p2.8xlarge | $0.70 | |
ml.p2.16xlarge | $1.00 | |
ml.p3.16xlarge | $2.00 |
Usage Information
Fulfillment Methods
Amazon SageMaker
Usage
See example notebook for example usage in python.
Output Sample
{
"results": {
"0_5": {
"other": 0.5300212651491165,
"Running": 0.16595888137817383,
"fighting": 0.09080103226006031,
"shooting": 0.07781386747956276,
"bull fighting": 0.03937860578298569
},
"5_10": {
"other": 0.8912457625071207,
"fighting": 0.04554063084651716,
"driving car": 0.025242092708746593,
"Running": 0.017623310287793476,
"bull fighting": 0.0051846196632444235
},
"10_15": {
"other": 0.9765619933605194,
"smoking": 0.009215933765517548,
"bull fighting": 0.006831713544670492,
"Running": 0.0034522799542173743,
"playing_musical_instrument": 0.0009778781386557966
}
}Metrics
Name | Regex |
|---|---|
Train-accuracy | .*\\[[0-9]+\\].*#011Train-accuracy:(\\S+) |
Train-loss | .*\\[[0-9]+\\].*#011Train-loss:(\\S+) |
Validation-accuracy | .*\\[[0-9]+\\].*#011Validation-accuracy:(\\S+) |
Validation-loss | .*\\[[0-9]+\\].*#011Validation-loss:(\\S+) |
Channel specification
Fields marked with * are required
train
*the train folder that includes video files for training. each sub-folder in this path determines a class
Input modes: File
Content types: video/*
Compression types: None
validation
the validation folder that includes video files for training. each sub-folder in this path determines a class
Input modes: File
Content types: video/*
Compression types: None
Hyperparameters
Fields marked with * are required
train_percent
data percentage for training
Type: Continuous
Tunable: No
val_percent
data percentage for validation
Type: Continuous
Tunable: No
learning_rate
Initial learning rate
Type: Continuous
Tunable: No
momentum
Momentum
Type: Continuous
Tunable: No
batch_size
*batch size(if set to 0, will automatically set batch size considering GPU memories)
Type: Integer
Tunable: No
lr_patience
Patience of LR scheduler
Type: Integer
Tunable: No
max_patience
Terminate training after validation loss become greater than train loss for this number of epochs
Type: Integer
Tunable: No
num_epochs
Total number of training epochs
Type: Integer
Tunable: No
num_samples_per_video
Number of samples to get from each video for training
Type: Integer
Tunable: No
num_result_tags
Number of tags(Top n tags) to show in each timestamp of Inference json file
Type: Integer
Tunable: No
score_result_threshold
Show the results that their score is greater than this threshold for each timestamp in Inference json file
Type: Continuous
Tunable: No
Additional Resources
End User License Agreement
By subscribing to this product you agree to terms and conditions outlined in the product End user License Agreement (EULA)
Support Information
AWS Infrastructure
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Learn MoreRefund Policy
You may cancel your subscription at any time; However, we will not refund payments made by you under the agreement for any reason whatsoever.
Customer Reviews
There are currently no reviews for this product.
View allWrite a review
Share your thoughts about this product.
Write a customer review