hello,
I am in the process of optimizing and quantizing a model for depth prediction, but even the smallest FP32 model variant is 150mb. I can either target the ESP32 or my PiZero, but id rather the ESP32 because it has many advantages for my particular project (and inference time is not a problem, even if it takes 20 minutes).
However, I DO need to know upfront whether its even worth the effort to quantize the model with ESP32 as target. So, I have an FP32 model at 150mb and an FP16 model at 75mb. lets say int8 quantization gets me a 4x size reduction. so we're looking at 37.5mb and 18.75mb for the quantized FP32 and FP16 models, respectively.
I only have an ESP32S3 with 8mb PSRAM. so, that leaves me with two final questions:
1. Does the ESP32 allow for (slow) VRAM swap space to be allocated on the SD card like linux does?
2. if not, i've read that ESP32S3 supports a maximum of 32mb PSRAM. does anyone know of a manufacturer actually making that configuration at the moment?
thanks
Maximum ESP-DL onnx model size?
Return to “General Discussion”
Jump to
- English Forum
- Explore
- News
- General Discussion
- FAQ
- Documentation
- Documentation
- Sample Code
- Discussion Forum
- Hardware
- ESP-IDF
- ESP-BOX
- ESP-ADF
- ESP-MDF
- ESP-WHO
- ESP-SkaiNet
- ESP32 Arduino
- IDEs for ESP-IDF
- ESP-AT
- ESP IoT Solution
- ESP RainMaker
- Rust
- ESP8266
- Report Bugs
- Showcase
- Chinese Forum 中文社区
- 活动区
- 乐鑫活动专区
- 讨论区
- 全国大学生物联网设计竞赛乐鑫答疑专区
- ESP-IDF 中文讨论版
- 《ESP32-C3 物联网工程开发实战》书籍讨论版
- 中文文档讨论版
- ESP-AT 中文讨论版
- ESP-BOX 中文讨论版
- ESP IoT Solution 中文讨论版
- ESP-ADF 中文讨论版
- ESP Mesh 中文讨论版
- ESP Cloud 中文讨论版
- ESP-WHO 中文讨论版
- ESP-SkaiNet 中文讨论版
- ESP 生产支持讨论版
- 硬件问题讨论
- 项目展示
Who is online
Users browsing this forum: No registered users and 59 guests
- All times are UTC
- Top
- Delete cookies
About Us
Espressif Systems is a fabless semiconductor company providing cutting-edge low power WiFi SoCs and wireless solutions for wireless communications and Internet of Things applications. ESP8266EX and ESP32 are some of our products.