Tracked topic
… It also supports MediaTek’s NeuroPilot SDK for AI workloads using frameworks such as PyTorch, ONNX Runtime, and TensorFlow Lite. …
… The system supports popular frameworks, including PyTorch, TensorFlow, ONNX, Keras, and Ultralytics YOLO, and utilizes C++ and Python APIs via the DX-RT inference engine. …
… It supports PyTorch, ONNX, TensorFlow, and Keras models via the DX-COM compiler, converting them to the proprietary DXNN format. …
… Boardcon Tiny1126B system-on-module Boardcon Tiny1126B specifications: SoC – Rockchip RV1126B CPU – Quad-core Arm Cortex-A53 up to 1.6 GHz with 32KB L1 I-Cache and 32KB L1 D-Cache, unified 512KB L2 Cache GPU – 2D Graphics Engine VPU Video Decoder – H.265/H.264 up to 3840×2160 @ 30fps Video Encoder … …
… Rikomagic DS08 specifications: SoC – Rockchip RK3588 CPU – Octa-core 64-bit Armv8 SoC with 4x Cortex-A76 cores @ 2.4GHz, 4x Cortex-A55 cores @ 1.8 GHz GPU – Arm Mali-G610 MP4 with support for OpenGL ES 3.2, OpenCL 2.2, Vulkan 1.1 NPU – Up to 6 TOPS, supports INT4/INT8/INT16, compatible with TensorF… …
… On the software side, the company notes that the SoCs now support the AMD ROCm open software stack for running standard AI frameworks such as PyTorch or TensorFlow without vendor lock-in. …
… Firefly CQ38W-1126B and CQ38W-3576 specifications: SoC CQ38W-1126B – Rockchip RV1126B or RV1126BJ industrial-grade version CPU – Quad-core Arm Cortex-A53 up to 1.6 GHz with 32KB L1 I-Cache and 32KB L1 D-Cache, unified 512KB L2 Cache GPU – 2D Graphics Engine VPU Video Decoder – H.265/H.264 up to 384… …
… Geniateach AP880 and AP880 mini specifications: SoC – NXP i.MX 8M Plus CPU – Quad-core Cortex-A53 processor @ 1.8GHz, Arm Cortex-M7 real-time core @ 800 MHz GPU – Vivante GC7000UL OpenGL ES 1.1, 2.0, 3.0, OpenCL 1.2, Vulkan support AI accelerator – 2.3 TOPS NPU VPU Encoder up to 1080p60 H.264, H.26… …
… Some code samples for the TinyEngine include: Generic time-series classification Arc fault AFCI Motor fault Electrocardiogram ECG The utility also allows users to capture data, train and optimize custom models, and leverage open-source frameworks built-in supporting PyTorch, TensorFlow, and ONNX. …