xujiashuai/cv_uhdm_image-demoireing
Model Introduction
Files & versions
Pull Requests
Discussion
Analysis

cv_uhdm_image-demoireing - Ascend NPU 适配

1. 模型简介

UHDM 图像去摩尔纹模型,基于 ESDNet (Encoder-decoder with Semantic alignment and Dense fusion) 架构,用于去除数字屏幕拍摄时产生的摩尔纹。

  • 原始模型: iic/cv_uhdm_image-demoireing
  • 框架: PyTorch + ModelScope
  • 任务: Image Demoireing (图像去摩尔纹)
  • Backbone: ESDNet (encoder-decoder + SAM)

2. 昇腾 NPU 适配结果

指标值
Cosine Similarity1.000000
Max Abs Error0.002218
平均延迟23.90ms
输出维度(1, 3, 64, 64)
推理精度float32
设备Ascend 910B4

3. 环境要求

组件版本
CANN8.5.1
torch_npu2.9.0.post1
PyTorch2.9.0
Python3.11
modelscopelatest

4. 快速使用

export ASCEND_HOME_PATH=/usr/local/Ascend/cann
export LD_LIBRARY_PATH=/usr/local/Ascend/cann/lib64:$LD_LIBRARY_PATH

python inference.py
python evaluate.py

5. 推理输出证据

Model: iic/cv_uhdm_image-demoireing
Device: npu:0
Output shape: [1, 3, 64, 64]
Output sample: [-0.0885179415345192, 0.3886769711971283, -0.39146584272384644, -0.15365758538246155, -0.45795387029647827]
Latency: 23.90ms

--- CPU vs NPU 精度对比 ---
Cosine Similarity: 1.000000
Max Abs Error: 0.002218
SUCCESS

6. CPU vs NPU 精度对比

指标CPU (float32)NPU (float32)误差
Cosine Similarity基准1.0000000
Max Abs Error-0.002218-
输出维度(1, 3, 64, 64)(1, 3, 64, 64)一致

7. 模型结构

  • Backbone: ESDNet (Encoder-decoder with Semantic alignment)
  • Encoder: 3-level encoder with RDB + SAM blocks
  • Decoder: 3-level decoder with CSAF fusion
  • Input: RGB image (padded to 32-divisible)
  • Output: Multi-scale restored images (tuple of 3)