mckero
c374058e1d
用户真机闪退回桌面且无任何 Java 日志 => 高度怀疑进程被系统 LMK 杀掉 (内存不足) 或 native 层崩溃。模型加载 + ONNX 引擎初始化存在瞬时内存峰值, fp32 模型 15MB 会放大这个峰值。 用 onnxruntime.quantization.quantize_dynamic 把模型权重动态量化为 QUInt8 (激活保持 float32): - 体积: 15,139,839 -> 4,248,808 字节 (缩小 71%) - 输入/输出名、形状、dtype 完全不变 -> Kotlin 代码无需改动 - 实测 CER (合成 CW 音频, fp32 vs int8 逐字符对比): SNR>=0dB 完全一致; -4dB 起两者一同劣化, 无显著差异 - onnx.checker 校验通过 AGPL 合规: NOTICE.md 记录派生信息 (原文件 SHA/量化后 SHA/转换步骤), 量化属模型修改, 按 AGPL 要求如实声明。复现命令已更新。 验证: :core:domain:test => 79 tests 全绿 (golden vector 测试锁定的是 频谱图前处理, 与模型文件无关)
3.6 KiB
Third-Party Notices — CW Decode Module
DeepCW neural CW decoding model
The CW (Morse code) decoder in this module performs inference with a neural network model obtained from the DeepCW project.
| Component | src/main/assets/deepcw/model.onnx and model.onnx.json |
| Upstream project | DeepCW / deepcw-engine |
| Source repository | https://github.com/e04/deepcw-engine |
| Author / copyright | e04 |
| License | GNU Affero General Public License v3.0 only (AGPL-3.0-only) |
| License text | DeepCW-AGPL-3.0.txt |
| Obtained at commit | 8e264d243bbd4467bd19f3f28292219405b47e0e |
| Original file size | 15,139,839 bytes |
| Original SHA-256 | ef120799457bca042d4690944f0faf93268eb4654e7f50f28784ad63bdc1fe02 |
| Derived file size | 4,248,808 bytes |
| Derived SHA-256 | cd48259be0ea8c30ecbfff4a718644f361cb27b9228b030771b0c94756dcab98 |
| Derivation | Dynamic int8 quantization (weights → QUInt8, activations stay float32) via onnxruntime.quantization.quantize_dynamic. Input/output names, shapes and dtypes are unchanged. Measured CER on synthetic CW audio is identical to the fp32 model at SNR >= -4 dB; at -6/-8 dB both models degrade similarly. |
Related upstream repositories by the same author (not vendored here):
- https://github.com/e04/web-deep-cw-decoder — reference web application
- https://github.com/e04/HamNoise — neural noise reduction (not used)
License compatibility
Look4Sat is licensed under the GNU General Public License v3.0 or later (GPL-3.0-or-later). The DeepCW model is licensed under AGPL-3.0-only.
Section 13 of the GPL version 3 expressly permits combining GPL-3.0 covered work with AGPL-3.0 covered work; the resulting combination may be conveyed, with the AGPL's additional network-interaction requirement applying to the AGPL-covered portion. Accordingly:
- The Look4Sat source code remains under GPL-3.0-or-later.
- The DeepCW model remains under AGPL-3.0-only.
- Distributions of the combined application are accompanied by complete corresponding source, satisfying both licenses.
AGPL section 13 (network interaction)
Inference runs entirely on the local device via ONNX Runtime. The application does not offer the model's functionality to users interacting with it remotely over a network, so the additional network-source-offer requirement of AGPL-3.0 section 13 is not triggered by this usage. The complete corresponding source for both the application and the vendored model remains publicly available at the repository hosting this file.
Reproducing the vendored files
# 1) Fetch the original fp32 model
SHA=8e264d243bbd4467bd19f3f28292219405b47e0e
curl -sLO https://raw.githubusercontent.com/e04/deepcw-engine/$SHA/model.onnx
curl -sLO https://raw.githubusercontent.com/e04/deepcw-engine/$SHA/model.onnx.json
curl -sL -o DeepCW-AGPL-3.0.txt \
https://raw.githubusercontent.com/e04/deepcw-engine/$SHA/LICENSE
sha256sum model.onnx
# expected: ef120799457bca042d4690944f0faf93268eb4654e7f50f28784ad63bdc1fe02
# 2) Reproduce the int8 quantization this repository ships
python - <<'PY'
from onnxruntime.quantization import quantize_dynamic, QuantType
quantize_dynamic("model.onnx", "model_int8.onnx", weight_type=QuantType.QUInt8)
PY
sha256sum model_int8.onnx
# expected: cd48259be0ea8c30ecbfff4a718644f361cb27b9228b030771b0c94756dcab98
# then copy model_int8.onnx over assets/deepcw/model.onnx
ONNX Runtime
Inference engine: com.microsoft.onnxruntime:onnxruntime-android, licensed
under the MIT License. Consumed as a published Maven artifact; not vendored in
this repository.