Hardware Guide
STMicroelectronics's STM32F7 is a solid choice for people counting using CMSIS-NN. The cortex-m7 core at 216 MHz with 512 KB SRAM accommodates 200 KB models with room for application logic. DSP extensions available.
| Spec | STM32F7 |
|---|---|
| Processor | ARM Cortex-M7 @ 216 MHz |
| SRAM | 512 KB |
| Flash | 2 MB |
| Key Features | Double-precision FPU, L1 cache (16 KB I + 16 KB D), ART Accelerator, Chrom-ART (DMA2D), TFT-LCD controller |
| Connectivity | Ethernet, USB OTG HS/FS |
| Price Range | $8 - $15 (chip), $25 - $60 (dev board) |
Memory-wise, the STM32F7 offers 512 KB SRAM, which delivers 2.7x the 192 KB minimum needed for people counting. The 200 KB quantized model fits in the tensor arena with enough remaining capacity for input buffers and core application logic. More demanding features (multi-sensor fusion, large protocol stacks) may require careful allocation planning. For firmware and model storage, the 2 MB flash accommodates the CMSIS-NN runtime and 200 KB model. Space remains for firmware and basic OTA capability. The STM32F7 at 216 MHz with Cortex-M7 instruction and data caches delivers near-real-time inference for mid-size models. Its 512 KB SRAM handles most sensor and audio ML workloads. The ART accelerator reduces flash access latency during inference. For people counting, connect a camera module (e.g., OV2640 via DVP/SPI) via SPI to the STM32F7. The camera interface supports QVGA (320×240) or lower resolution for on-device inference. Downsample to the model's input size (typically 96×96 or 128×128 pixels) before feeding the neural network. CMSIS-NN provides ARM-optimized neural network kernels that leverage the STM32F7's DSP instructions and floating-point unit for maximum inference throughput on Cortex-M. The kernels are hand-optimized in assembly for critical operations (Conv2D, DepthwiseConv2D, FullyConnected). Combine with TFLite Micro's CMSIS-NN delegate for the best performance on ARM targets. At $8-15 per chip ($25-60 for dev boards), the STM32F7 is a reasonable investment for people counting deployments. Key STM32F7 features for this workload: Double-precision FPU, L1 cache (16 KB I + 16 KB D), ART Accelerator, Chrom-ART (DMA2D), TFT-LCD controller.
Set up STM32F7 development environment
Install STM32CubeIDE with the latest STM32Cube firmware package. Create a project targeting the STM32F7 and verify basic functionality (blink LED, serial output). For CMSIS-NN, clone the framework repository and add it as a library dependency. Ensure the toolchain supports C++11 or later for the ML runtime.
Collect camera training data
Connect a camera module (e.g., OV2640 via DVP/SPI) to the STM32F7. Write a data logging sketch that captures camera readings at the target sample rate and outputs via serial/SD card. Collect 1000+ labeled samples across all classes. Capture images at the model input resolution (96×96 or lower).
Train model and prepare for CMSIS-NN deployment
Train a quantized MobileNet-SSD or YOLO-Tiny in TensorFlow/Keras. Apply int8 post-training quantization via the TFLite converter — this is essential for CMSIS-NN's optimized kernels. The quantized model should be under 200 KB. Use tflite_micro's CMSIS-NN delegate to automatically route operations to optimized ARM kernels on the STM32F7's cortex-m7 core.
Deploy and validate on STM32F7
Include the CMSIS-NN runtime and compiled model in your STMicroelectronics project. Allocate a tensor arena of 300-500 KB in a static buffer. Run inference on live camera data and compare predictions against your test set. Log results to serial for desktop validation. Measure inference latency and peak RAM usage to verify they meet application requirements.
STMicroelectronics cortex-m7 at 480 MHz with 1024 KB SRAM. $8-20 per chip. Compared to STM32F7: more RAM, faster clock. Excellent rated.
NXP cortex-m7 at 600 MHz with 1024 KB SRAM. $6-12 per chip. Compared to STM32F7: more RAM, faster clock, cheaper. Excellent rated.
STMicroelectronics cortex-m33 at 160 MHz with 786 KB SRAM. $6-15 per chip. Compared to STM32F7: more RAM, cheaper. Good rated.
Connect cameras to on-device inference — design detection workflows visually and compile to optimized firmware.
Get Started Free