| Model Type | Quantized CNN for Classification |
|---|---|
| Framework | LiteRT (TensorFlow Lite) |
| Algorithm | ShuffleNet v2 (Quantized) |
| Technical Details | ShuffleNet v2 is a compact and high-performance convolutional neural network designed for real-time image classification on edge devices. This implementation utilizes a quantized TFLite model to enable efficient deployment on low-resource processors. Ideal for smart IoT devices, vision sensors, and applications requiring responsive classification in constrained environments. The architecture combines group convolution and channel shuffle operations to minimize memory and computation load. |
Image Classification
Efficient CNN model for image classification on mobile and embedded edge devices.
Leave your message here
Fill the form with the required information
$0.00
Image Classification
app details
Resources
Use Cases
Quality Control
Supported SECO Devices
AI optimized hardware
Fanless embedded PCs
Modules
supported chipsets
Intel® Core™ i3
Qualcomm® Dragonwing QCS6490
Qualcomm® Dragonwing QCS5430
NXP i.MX 8M Plus
NXP i.MX 95
Performance Benchmark
Hardware
Latency (ms)
Memory Usage
Processing unit
SECO SOM-SMARC-QCS6490
3.97 ms
0.36 MB
CPU
SECO SOM-SMARC-QCS6490
1.04 ms
0.36 MB
NPU
SECO SOM SMARC iMX8Plus
52.34 ms
0.36 MB
CPU
SECO SOM SMARC iMX8Plus
17.93 ms
0.36 MB
NPU
SECO SOM-SMARC-MX95
19.11 ms
0.36 MB
CPU
SECO Titan 300 TGL-UP3 AI
2.83 ms
0.36 MB
CPU
Automated Quality Inspection with Vision AI
Real-time AI-powered vision system for detecting defects in manufacturing environments
View Model
YAMNet for Environmental Sound Classification
Real-time environmental sound classifier optimized for low-power edge devices using MobileNet v1.
View Model
FFNet for Real-Time Semantic Segmentation
Lightweight semantic segmentation model optimized for real-time street scene analysis on edge devices.
View Model|
|