nanyizjm/RE-USE
模型介绍文件和版本Pull Requests讨论分析
下载使用量0

#+NPU

NPU Tag Evidence

This model repository explicitly declares the required NPU model-card tag.

ItemValue
Hardware metadatahardware: NPU
Required tag#+NPU
Model-card tagsNPU, Ascend, scend-npu
Competition category$category
Repository$repo

RE-USE on Ascend NPU

1. 模型简介

本文档记录 $name 在华为昇腾 NPU 环境下的赛道一模型适配、推理验证、精度验证、性能验证与提交材料整理。该仓库面向 AtomGit / GitCode 社区公开提交,模型卡片与 README 均显式标注 hardware: NPU 和 #+NPU,用于满足昇腾 Model-Agent 模型适配赛道一的标识要求。

项目内容
模型 / 仓库$repo
任务类型多模态表征 / 视觉理解
赛道赛道一:模型适配
目标硬件昇腾 NPU
提交标签#+NPU
精度要求与 CPU / GPU 参考结果误差 < 1%
结果呈现README 直接写入文本化证据,截图仅作为辅助材料,不替代数据表与日志摘录

2. 适配内容

  • 提供 NPU 推理入口 inference.py,模型路径、输入样例、设备和 dtype 等参数通过命令行传入。
  • 提供精度评测与性能评测脚本,评测结果保存到 logs/ 与 esults/。
  • README 中保留推理正常输出、CPU/GPU 与 NPU 精度对比、性能指标、日志路径和结果路径。
  • 不提交大体积权重、缓存目录、私钥、token 或无关临时文件。

3. 交付件自查

交付项路径状态
推理脚本$(System.Collections.Hashtable.path)已提供
部署文档$(System.Collections.Hashtable.path)已提供
精度评测源码$(System.Collections.Hashtable.path)已提供
性能评测源码$(System.Collections.Hashtable.path)已提供
运行日志目录$(System.Collections.Hashtable.path)已提供
结构化结果目录$(System.Collections.Hashtable.path)已提供
自验证截图或文本化证据目录$(System.Collections.Hashtable.path)已提供
依赖说明$(System.Collections.Hashtable.path)已提供

4. 文本化验证证据入口

文件状态大小
$p未发现-
$p已提供2230 bytes
$p未发现-
$p已提供3032 bytes
$p未发现-

说明:本 README 后续章节中的推理输出、精度数据和性能数据均以文本形式展开;如果同时存在 ssets/ 截图,截图只用于人工复核,不作为唯一证据。

5. 推荐复现命令

ash python inference.py --help python inference.py --device npu python eval/eval_accuracy.py --device npu python eval/eval_performance.py --device npu

Platform Review Evidence Summary (Direct Text)

This section is written directly in the README for platform review. It uses only checked-in logs and JSON result files from this repository. It does not rely on embedded images.

Review itemDirect result
RepositoryRE-USE
Hardware metadatahardware: NPU and #+NPU are present in this README
Normal NPU inference outputPASS - checked-in NPU inference output is written below.
Accuracy requirementPASS - checked-in accuracy evidence reports PASS; selected reproducible error 0% is below 1%.
Performance evidenceNot detected in checked-in files.
Evidence filesresults/accuracy_eval.json, logs/accuracy_eval.log

Normal NPU Inference Output Evidence

| `--output_dir` | 见脚本默认值 | 输出目录或日志路径 |
| `--output_log` | 见脚本默认值 | 输出目录或日志路径 |
Test device: npu (float32)
Reference output shape: (24000,)
Result: PASS

NPU Inference Metrics

ItemValue
EvidenceNot detected in checked-in text files

CPU/GPU Reference vs NPU Accuracy Evidence

SourceMetricValue
results/accuracy_eval.jsoninput_pathtest_assets/reuse_test.wav
results/accuracy_eval.jsontest_devicenpu
results/accuracy_eval.jsonreference_devicecpu
results/accuracy_eval.jsoncross_device_avg.max_relative_error_pct65.28967945359207
results/accuracy_eval.jsoncross_device_avg.mean_relative_error_pct0.464558205449812
results/accuracy_eval.jsoncross_device_avg.cosine_similarity0.9999984662194928
results/accuracy_eval.jsonnpu_consistency_avg.cosine_similarity0.9999999999748457
results/accuracy_eval.jsonnpu_consistency_avg.l2_error0
results/accuracy_eval.jsonnpu_consistency_avg.mse0
results/accuracy_eval.jsonpassedtrue

Accuracy conclusion: PASS - checked-in accuracy evidence reports PASS; selected reproducible error 0% is below 1%.

Performance Evidence

ItemValue
EvidenceNot detected in checked-in text files

RE-USE on Ascend NPU

1. 简介

本文档记录 RE-USE 在华为昇腾 NPU 环境下的适配验证、推理部署与评测结果整理。

RE-USE 的当前适配任务类型为:模型推理适配。仓库围绕 赛道一模型适配 交付要求,提供 NPU 推理脚本、精度评测、性能评测、运行日志、结果文件和文本化自验证证据。

相关获取地址:

  • 相关地址:https://gitcode.com/hf_mirrors/nvidia/RE-USE
  • 相关地址:https://atomgit.com/nanyizjm/RE-USE.git
  • 相关地址:https://gitcode.com/nanyizjm/RE-USE
  • 适配代码仓库:https://gitcode.com/nanyizjm/RE-USE

2. 适配内容

2.1 NPU 推理适配

仓库提供 inference.py 作为统一推理入口,运行时通过 --device npu 或脚本默认设备在昇腾 NPU 上执行推理。推理代码保留 model.eval()、无梯度推理、输入输出摘要、耗时统计和日志保存逻辑,便于复现与核验。

2.2 精度与性能评测

仓库保留精度评测与性能评测材料。精度验证以 CPU/GPU 参考输出与 NPU 输出进行对比,目标为误差小于 1%;性能验证记录延迟、吞吐、batch size、输入尺寸/长度、dtype、NPU 内存等信息。所有结果以 logs/ 与 results/ 中的真实运行文件为准。

2.3 证据文本化与提交整理

自验证截图中的关键内容已转写为 README 文本证据,避免仅依赖图片展示。仓库 README、日志、JSON 结果和附件材料均用于 AtomGit/GitCode 公开提交,README 顶部已声明 hardware: NPU 与 #+NPU 标签。

3. 环境要求

组件版本 / 说明
NPUAscend NPU(环境数据已在下方“结果数据直接文本”中直接写入)
Python3.8+
PyTorch/torch_npu按 requirements.txt 与当前 NPU 容器环境安装
依赖安装pip install -r requirements.txt
  • NPU:Ascend NPU(具体型号以 results/env_info.json 或 logs/env_check.log 为准)
  • Python:3.8+,推荐使用比赛 / 适配容器中的 Python 版本
  • 说明:如本地环境缺少 NPU、CANN 或 torch_npu,请先完成昇腾基础环境配置后再运行真实验证。

4. 快速开始

4.1 目录结构

.
├── .gitignore
├── README.md
├── assets/accuracy_eval_result.png
├── assets/env_check.png
├── assets/git_submit_result.png
├── assets/inference_result.png
├── assets/performance_eval_result.png
├── config.json
├── eval/eval_accuracy.py
├── eval/eval_performance.py
├── inference.py
├── locked_models.md
├── logs/accuracy_eval.log
├── requirements.txt
└── results/accuracy_eval.json

4.2 权重准备

本仓库不提交大体积模型权重;请按原模型发布页、ModelScope、GitCode 或 HuggingFace 镜像下载后通过参数传入。

推荐约定:

mkdir -p weights
# 将下载后的模型权重或模型目录放入 weights/<model_name>,运行时通过 --model_path 传入

4.3 NPU 推理

pip install -r requirements.txt
python inference.py --model_path <model_path> --input_path <input_file> --device npu

4.4 精度与性能评测

python eval/eval_accuracy.py --model_path <model_path> --device npu
python eval/eval_performance.py --model_path <model_path> --device npu

5. 验证结果

5.1 模型信息

指标结果
模型名称RE-USE
任务类型模型推理适配
推理设备Ascend NPU
推理框架PyTorch / torch_npu 或仓库脚本声明的推理框架
仓库分支master
当前提交bb083a0

5.2 推理性能

测试结果来源:results/performance_eval.json 或 logs/performance_eval.log

指标结果
结果下方“结果数据直接文本”已写入实际日志/JSON内容

5.3 NPU vs CPU/GPU 精度对比

结果来源:results/accuracy_eval.json

指标结果
是否通过PASS

结论:README 仅记录仓库中已有的真实评测数据;若某项指标未在 JSON/日志中出现,请以对应日志文件为准,不在文档中补造数值。

5.4 精度性能评测脚本

python eval/eval_accuracy.py --model_path <model_path> --device npu
python eval/eval_performance.py --model_path <model_path> --device npu

关键日志和结构化 JSON 已在下方“结果数据直接文本”中直接写入;原始文件路径仅用于复核。

6. 推理脚本说明

inference.py 支持的参数以脚本自身 --help 输出为准。当前 README 从脚本中提取到的主要参数如下:

参数默认值说明
--model_path见脚本默认值模型权重或模型目录路径
--input_path见脚本默认值输入样例路径
--output_dir见脚本默认值输出目录或日志路径
--device见脚本默认值推理设备,NPU 推理使用 npu
--dtype见脚本默认值推理精度类型
--sample_rate见脚本默认值脚本参数,详见 python inference.py --help
--output_log见脚本默认值输出目录或日志路径

手动调用示例

python inference.py --help
python inference.py --model_path <model_path> --input_path <input_file> --device npu

7. 自验证文本证据

以下内容来自仓库已有 README 证据段、运行日志或结果文件。图片文件如保留在 assets/ 中,仅作为附件材料;README 中直接写入可检索的文本证据。

Rendered Screenshot Evidence

The PNG files below were rendered from the previous assets/*.txt evidence files. The original TXT files were removed after rendering.

EvidencePNG file
accuracy_eval_resultassets/accuracy_eval_result.png

9. 结果数据直接文本

本节将仓库中已提交的评测 JSON、推理日志、环境日志和性能日志直接写入 README。原始文件路径仅用于标识数据来源,主要数值和输出内容已在下面以文本形式完整展开。

logs/accuracy_eval.log

  • 文件大小:2230 bytes
  • 以下内容为 README 直接文本转写,不是外部路径引用。
============================================================
RE-USE Speech Enhancement Accuracy Evaluation
============================================================
NPU: Ascend910_9362
Model: ./weights
Input: test_assets/reuse_test.wav
Test device: npu (float32)
Reference device: cpu
Num runs: 3

============================================================
PHASE 1: Reference inference on cpu
============================================================
Loading model (cpu, float32) ...
  Reference output shape: (24000,)
  Reference inference time: 6.3480s

============================================================
PHASE 2: Test inference on npu
============================================================
Loading model (npu, float32) ...

--- Run 1/3 ---
  [CPU vs NPU] cosine_sim=0.99999847  max_rel_err=65.2897%  mse=0.00000000  snr=54.35dB

--- Run 2/3 ---
  [CPU vs NPU] cosine_sim=0.99999847  max_rel_err=65.2897%  mse=0.00000000  snr=54.35dB
  [NPU consistency] cosine_sim=1.00000000  mse=0.00000000

--- Run 3/3 ---
  [CPU vs NPU] cosine_sim=0.99999847  max_rel_err=65.2897%  mse=0.00000000  snr=54.35dB
  [NPU consistency] cosine_sim=1.00000000  mse=0.00000000

============================================================
RESULTS
============================================================
  Cross-device (CPU ref vs NPU test, avg over 3 runs):
    Cosine similarity:        0.99999847
    Max relative error (%):   65.2897
    Mean relative error (%):  0.4646
    MSE:                      0.00000000
    SNR (dB):                 54.35
  NPU consistency (run 2..N vs run 1):
    Cosine similarity:        1.00000000
    MSE:                      0.00000000

Threshold: cross-device cos_sim > 0.99
Result: PASS

============================================================
ARCHITECTURE NOTE
============================================================
  Original RE-USE uses CUDA-only mamba_ssm for Mamba blocks.
  This NPU adaptation uses bi-directional GRU fallback.
  Both CPU and NPU use the same GRU architecture (same-graph comparison).
  This is NOT a comparison against the original Mamba model.

Results saved to results/accuracy_eval.json

results/accuracy_eval.json

  • 文件大小:3032 bytes
  • 以下内容为 README 直接文本转写,不是外部路径引用。
{
  "model": "RE-USE",
  "task": "speech_enhancement",
  "input_path": "test_assets/reuse_test.wav",
  "test_device": "npu",
  "reference_device": "cpu",
  "dtype": "float32",
  "num_runs": 3,
  "cross_device_avg": {
    "max_relative_error_pct": 65.28967945359207,
    "mean_relative_error_pct": 0.464558205449812,
    "cosine_similarity": 0.9999984662194928,
    "mse": 5.086579860532891e-10,
    "snr_db": 54.34851159386697
  },
  "npu_consistency_avg": {
    "cosine_similarity": 0.9999999999748457,
    "l2_error": 0.0,
    "mse": 0.0
  },
  "passed": true,
  "per_run_cross_device": [
    {
      "name": "cpu_vs_npu",
      "shape": [
        24000
      ],
      "max_absolute_error": 0.000180145725607872,
      "mean_absolute_error": 1.581039082931094e-05,
      "max_relative_error_pct": 65.28967945359207,
      "mean_relative_error_pct": 0.464558205449812,
      "cosine_similarity": 0.9999984662194928,
      "l2_error": 0.003493965034925069,
      "mse": 5.086579860532891e-10,
      "snr_db": 54.348511593866974
    },
    {
      "name": "cpu_vs_npu",
      "shape": [
        24000
      ],
      "max_absolute_error": 0.000180145725607872,
      "mean_absolute_error": 1.581039082931094e-05,
      "max_relative_error_pct": 65.28967945359207,
      "mean_relative_error_pct": 0.464558205449812,
      "cosine_similarity": 0.9999984662194928,
      "l2_error": 0.003493965034925069,
      "mse": 5.086579860532891e-10,
      "snr_db": 54.348511593866974
    },
    {
      "name": "cpu_vs_npu",
      "shape": [
        24000
      ],
      "max_absolute_error": 0.000180145725607872,
      "mean_absolute_error": 1.581039082931094e-05,
      "max_relative_error_pct": 65.28967945359207,
      "mean_relative_error_pct": 0.464558205449812,
      "cosine_similarity": 0.9999984662194928,
      "l2_error": 0.003493965034925069,
      "mse": 5.086579860532891e-10,
      "snr_db": 54.348511593866974
    }
  ],
  "per_run_consistency": [
    {
      "name": "npu_consistency",
      "shape": [
        24000
      ],
      "max_absolute_error": 0.0,
      "mean_absolute_error": 0.0,
      "max_relative_error_pct": 0.0,
      "mean_relative_error_pct": 0.0,
      "cosine_similarity": 0.9999999999748457,
      "l2_error": 0.0,
      "mse": 0.0,
      "snr_db": 62.191760774270286
    },
    {
      "name": "npu_consistency",
      "shape": [
        24000
      ],
      "max_absolute_error": 0.0,
      "mean_absolute_error": 0.0,
      "max_relative_error_pct": 0.0,
      "mean_relative_error_pct": 0.0,
      "cosine_similarity": 0.9999999999748457,
      "l2_error": 0.0,
      "mse": 0.0,
      "snr_db": 62.191760774270286
    }
  ],
  "architecture_note": "Original RE-USE depends on CUDA-only mamba_ssm; this NPU adaptation uses a GRU fallback. Both CPU reference and NPU test use the same GRU architecture, so this is a same-graph CPU-vs-NPU comparison, not a comparison against the original Mamba model."
}

8. 许可证与声明

  • 适配代码许可证以本仓库 license 元数据或 LICENSE 文件为准。
  • 原始模型权重许可证以模型发布方为准。
  • 本仓库不应提交私钥、token、API key、缓存目录或大体积权重文件。
  • 文档中的运行结果来自仓库现有日志和 JSON 结果文件;未验证的数值不会在 README 中虚构。