Contact Us
Optimal for your device
I want to create an AI model
Implementation on the device
I have concerns
Deployed to device, but
No speed
We listen to the customer's requirements and conduct profiling of the current inference process. After sorting out the required latency and accuracy performance, we define the requirements for the optimal model. If it is not necessary to do this at the edge, we will consider sharing the work with the cloud.
Current
inference processing time.
Profiling
Required
Latency/FPS
Definition of
Required
Definition of accuracy performance
Model Deployment/
How to update
Consider
Edge and Cloud
Define the division of
We receive model files and code from the customer and convert, optimize, and evaluate models for candidate edge devices. If the model file is not available, we can develop a model that meets the required accuracy and speed.
Preparing a model
or developed by us
Conversion and optimization for candidate devices
Perform requirement inference speed
Evaluate
Myriad X, Edge TPU, Hailo, Ambarella
Raspberry Pi, NXP i.MX RT
Arria10/SoC, Zynq Ultrascale+ MPSoC
NVIDIA Jetson Series
iPhone, iPad, Android, SNPE
AITRIOS™ COMPATIBLE MODELS (WITH IMX500)
Jetson AGX Orin-equipped models
Models with Hailo-8
Upon receiving the created model, input/output data, training code, etc., we will propose methods to make the model smaller. In addition to optimization using development tools for each edge device, there are various methods for weight reduction and miniaturization, such as pruning the model branches and applying quantization individually.
Experienced engineers use development tools appropriately,
to maximize performance.
Industry: Manufacturing
Challenge: Needed a lightweight, more accurate model to drive edginess in factory anomaly detection tasks.
Industry: Retail
Problem: The customer product detection model has a processing time issue due to the large number of images to be processed.
Listed in Japanese alphabetical order
