微信公众号 讲师中心
首页
文章
后端开发 web前端 数据库 开发工具 php框架 常见问题 科技 Java 系统教程 电脑教程 硬件教程 手机教程 软件教程 游戏教程 自媒体 新闻
专题
后端开发 web前端 数据库 开发工具 php框架 科技 Java 系统教程 电脑教程 硬件教程 手机教程 软件教程 游戏教程 新闻
AI工具
AI 聊天问答 Agent智能体 AI 文本写作 AI 绘画作图 AI 设计工具 AI 视频创作 AI 音频制作 AI 办公学习 AI 编程开发 Prompt指令
学习
大前端 后端开发 数据库 移动端 运维开发 计算机基础
编程手册
大前端 后端开发 数据库 移动端 运维开发 计算机基础
下载
js特效 网站源码 工具下载 类库下载 网站素材 学习资源 插件扩展 手机/移动开发 手机游戏
搜索
后端开发 web前端 数据库 开发工具 php框架 常见问题 科技 Java 系统教程 电脑教程 硬件教程 手机教程 软件教程 游戏教程
自媒体 新闻
首页 > 科技周边 > 人工智能 > 正文

【论文复现】PatchCore: 面向全召回率的工业异常检测

P粉084495128
发布： 2025-07-22 10:51:18
原创
632人浏览过
本文基于PaddlePaddle复现PatchCore工业异常检测算法，改进特征提取与筛选，用KNN Greedy CoreSet采样构建记忆池，采用新策略算异常得分。在MVTec数据集精度达标，还介绍了相关流程与复现心得。

☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 免费无限量使用 DeepSeek R1 模型☜☜☜

【论文复现】patchcore: 面向全召回率的工业异常检测 - php中文网

PatchCore: Towards Total Recall in Industrial Anomaly Detection

1. 简介

本项目基于PaddlePaddle框架复现了PatchCore算法，并在MvTec数据集上进行了实验。【论文复现】PatchCore: 面向全召回率的工业异常检测 - php中文网        

PatchCore对SPADE,PaDiM等一系列基于图像Patch的无监督异常检测算法工作进行了扩展，主要解决了SPADE测试速度太慢的问题，并且在特征提取部分做了一些探索。相比SPADE,PaDiM，PatchCore 仅使用stage2、stage3的特征图进行建模，通过增加窗口大小为3、步长为1、padding为1的平均池化AvgPool2d增大感受野后拼接，使用KNN Greedy CoreSet 采样选取最具代表性的特征点（选择与其他特征点最远的点以实现尽可能平衡的采样，效果类似泊松圆盘）,构建特征向量记忆池，只保留1%~10%的特征数，进而实现高效的特征筛选并用于异常检测。并提出采用了re-weighting策略计算Image-Level的异常得分代替此前的最大值异常得分。 PatchCore 论文: PatchCore: Towards Total Recall in Industrial Anomaly Detection

参考repo:

  • anomalib

在此非常感谢openvineo贡献的anomalib项目，提高了本repo复现论文的效率。

本项目为第六届论文复现赛异常检测项目。

  • 感谢百度提供的算力支持。

2 复现精度

按复现考核标准，使用resnet18 10%特征数 在MVTec AD数据集的测试效果如下表。

category Image_AUROC Pixel_AUROC PRO_score
carpet 0.995586 0.990199 0.959082
grid 0.969925 0.979229 0.921544
leather 1 0.989842 0.969135
tile 0.989899 0.940809 0.847143
wood 0.990351 0.943459 0.889898
bottle 1 0.9814 0.945257
cable 0.977699 0.984428 0.941403
capsule 0.979657 0.989979 0.942688
hazelnut 1 0.988504 0.936284
metal_nut 0.993157 0.985884 0.938088
pill 0.938352 0.97595 0.92767
screw 0.938512 0.993937 0.971481
toothbrush 0.936111 0.990976 0.917974
transistor 0.990417 0.955586 0.915834
zipper 0.971113 0.987035 0.954973
mean 0.978052 0.978481 0.931897

Image-Level AUC


 Avg Carpet Grid Leather Tile Wood Bottle Cable Capsule Hazelnut Metal Nut Pill Screw Toothbrush Transistor Zipper
anomalib (ResNet-18) 0.973 0.970 0.947 1.000 0.997 0.997 1.000 0.986 0.965 1.000 0.991 0.916 0.943 0.931 0.996 0.953
复现 0.978052 0.995586 0.969925 1 0.989899 0.990351 1 0.977699 0.979657 1 0.993157 0.938352 0.938512 0.936111 0.990417 0.971113

Pixel-Level AUC


 Avg Carpet Grid Leather Tile Wood Bottle Cable Capsule Hazelnut Metal Nut Pill Screw Toothbrush Transistor Zipper
ResNet-18 0.976 0.986 0.955 0.990 0.943 0.933 0.981 0.984 0.986 0.986 0.986 0.974 0.991 0.988 0.974 0.983
复现 0.978481 0.990199 0.979229 0.989842 0.940809 0.943459 0.9814 0.984428 0.989979 0.988504 0.985884 0.97595 0.993937 0.990976 0.955586 0.987035

达到论文复现验收标准.

3 数据集准备

In [1]
%cd /home/aistudio/data/
!tar xvf data116034/mvtec_anomaly_detection.tar.xz >/dev/null
登录后复制
       
/home/aistudio/data
登录后复制
       

4 依赖安装

In [1]
!pip install scikit-image >/dev/null
登录后复制
       
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
parl 1.4.1 requires pyzmq==18.1.1, but you have pyzmq 22.3.0 which is incompatible.
登录后复制
       

5 训练

一共有15个类别，这里需要对15个类别分别训练，最后取平均值作为验证指标.(https://github.com/openvinotoolkit/anomalib/blob/development/anomalib/models/stfpm/README.md).

单个类别训练： 以category=carpet为例。

In [3]
%cd /home/aistudio/Anomaly.Paddle/
!python train.py --category carpet --data_path=/home/aistudio/data/ --method=coreset --arch=resnet18 --k=10 --eval
登录后复制
       
/home/aistudio/Anomaly.Paddle
Namespace(arch='resnet18', batch_size=32, category='carpet', cpu=False, crop_size=256, data_path='/home/aistudio/data/', debug=False, einsum=False, eval=True, eval_PRO=False, eval_threthold_step=500, inc=False, k=10, load_projection=None, method='coreset', non_partial_AUC=False, num_workers=0, resize=256, save_model=True, save_model_subfolder=True, save_path='./output/coreset_resnet18_10', save_pic=True, seed=521, test_batch_size=1)
W0505 22:47:52.097200   463 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 22:47:52.102414   463 device_context.cc:465] device: 0, cuDNN Version: 7.6.
100%|██████████████████████████████████| 69183/69183 [00:04<00:00, 14500.91it/s]
model resnet18, nParams 2787264
Training model 1/1 for carpet
| feature extraction | train | carpet |:   0%|            | 0/9 [00:00<?, ?it/s]/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
| feature extraction | train | carpet |: 100%|████| 9/9 [00:20<00:00,  2.27s/it]
Creating CoreSet Sampler via k-Center Greedy
Getting the coreset from the main embedding.
Assigning the coreset as the memory bank with shape [28672, 384].
2022-05-05 23:06:01	Train ends, total 1067.16s
Saving model...
2022-05-05 23:06:01	Save model in ./output/coreset_resnet18_10/carpet.pdparams
2022-05-05 23:06:01	Starting eval model...
| feature extraction | test | carpet |: 100%|█| 117/117 [02:26<00:00,  1.25s/it]
max_score:3.2409136295318604 min_score:0.7035042643547058
F1 image:0.9828571428571428 threshold:3.2409136295318604
F1 pixel:0.5584764361267536 threshold:3.2409136295318604
['carpet', 0.9955858747993579, 0.9901991232207019, None]
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2349: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  if isinstance(obj, collections.Iterator):
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:101: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  ret = np.asscalar(ex)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2366: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  return list(data) if isinstance(data, collections.MappingView) else data
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:425: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_min = np.asscalar(a_min.astype(scaled_dtype))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:426: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_max = np.asscalar(a_max.astype(scaled_dtype))
          Image_AUROC  Pixel_AUROC
category                          
carpet       0.995586     0.990199
Evaluation result saved at./output/coreset_resnet18_10/carpet_seed521.csv:
登录后复制
       

对所有类别进行训练：

In [4]
%cd /home/aistudio/Anomaly.Paddle/
!python train.py --category all --data_path=/home/aistudio/data/ --method=coreset --arch=resnet18 --k=10 --eval
登录后复制
       
/home/aistudio/Anomaly.Paddle
Namespace(arch='resnet18', batch_size=32, category='all', cpu=False, crop_size=256, data_path='/home/aistudio/data/', debug=False, einsum=False, eval=True, eval_PRO=False, eval_threthold_step=500, inc=False, k=10, load_projection=None, method='coreset', non_partial_AUC=False, num_workers=0, resize=256, save_model=True, save_model_subfolder=True, save_path='./output/coreset_resnet18_10', save_pic=True, seed=521, test_batch_size=1)
W0505 23:08:38.231904  2381 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:08:38.237079  2381 device_context.cc:465] device: 0, cuDNN Version: 7.6.
^C
登录后复制
       

6 测试

单个类别测试： 以category=carpet为例。

In [13]
%cd /home/aistudio/Anomaly.Paddle/
!python eval.py --data_path=/home/aistudio/data/ --category carpet --method=coreset --arch=resnet18 --k=10
登录后复制
       
/home/aistudio/Anomaly.Paddle
Namespace(arch='resnet18', batch_size=1, category='carpet', crop_size=256, data_path='/home/aistudio/data/', eval_PRO=False, eval_threthold_step=500, k=10, method='coreset', model_path=None, non_partial_AUC=False, num_workers=0, resize=256, save_path='./output/coreset_resnet18_10', save_pic=True, seed=521, test_batch_size=1)
Testing model 1/1 for carpet
W0505 23:14:08.773208  3548 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:14:08.778220  3548 device_context.cc:465] device: 0, cuDNN Version: 7.6.
model resnet18, nParams 2787264
2022-05-05 23:14:18	Starting eval model...
| feature extraction | test | carpet |:   0%|           | 0/117 [00:00<?, ?it/s]/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
| feature extraction | test | carpet |: 100%|█| 117/117 [01:38<00:00,  1.19it/s]
max_score:3.2409136295318604 min_score:0.7035042643547058
F1 image:0.9828571428571428 threshold:3.2409136295318604
F1 pixel:0.5584764361267536 threshold:3.2409136295318604
['carpet', 0.9955858747993579, 0.9901991232207019, None]
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2349: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  if isinstance(obj, collections.Iterator):
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:101: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  ret = np.asscalar(ex)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2366: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  return list(data) if isinstance(data, collections.MappingView) else data
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:425: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_min = np.asscalar(a_min.astype(scaled_dtype))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:426: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_max = np.asscalar(a_max.astype(scaled_dtype))
          Image_AUROC  Pixel_AUROC
category                          
carpet       0.995586     0.990199
Evaluation result saved at./output/coreset_resnet18_10/carpet_seed521.csv:
登录后复制
       

对所有类别进行测试： 由于已在训练过程中进行测试此处不再重复

魔匠AI论文
魔匠AI论文

专业原创的AI论文写作工具，一站式解决论文选题、写作、文献综述、答辩PPT全流程，支持毕业论文、课程论文等多种类型，轻松助力高质量论文写作。

魔匠AI论文 53
查看详情 魔匠AI论文
In [6]
#%cd /home/aistudio/Anomaly.Paddle/#!python eval.py --data_path=/home/aistudio/data/ --category all --method=coreset --arch=resnet18 --k=10 --eval_PRO
登录后复制
   

7 单独预测

In [7]
%cd /home/aistudio/Anomaly.Paddle/
!python predict.py /home/aistudio/data/carpet/test/color/000.png --category carpet --method=coreset --arch=resnet18 --k=10
登录后复制
       
/home/aistudio/Anomaly.Paddle
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
Namespace(arch='resnet18', category='carpet', crop_size=256, k=10, method='coreset', model_path=None, norm=True, picture_path='/home/aistudio/data/carpet/test/color/000.png', resize=256, save_path='./output/coreset_resnet18_10', save_pic=True, seed=42, threshold=0.4)
Testing model for carpet
W0505 23:11:38.219069  2823 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:11:38.224303  2823 device_context.cc:465] device: 0, cuDNN Version: 7.6.
model resnet18, nParams 2787264
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
2022-05-05 23:11:53	Starting eval model...
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2349: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  if isinstance(obj, collections.Iterator):
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:101: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  ret = np.asscalar(ex)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2366: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  return list(data) if isinstance(data, collections.MappingView) else data
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:425: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_min = np.asscalar(a_min.astype(scaled_dtype))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:426: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_max = np.asscalar(a_max.astype(scaled_dtype))
2022-05-05 23:11:55	Predict :  Picture /home/aistudio/data/carpet/test/color/000.png done!
Result saved at ./output/coreset_resnet18_10/carpet/carpet_predict.png
登录后复制
       

可以在output/找到如下的类似结果：

8 导出

In [8]
%cd /home/aistudio/Anomaly.Paddle/
!python export_model.py --method=coreset --arch=resnet18 --k=10 --model_path=./output/coreset_resnet18_10/carpet.pdparams --save_dir=./output/coreset_resnet18_10
登录后复制
       
/home/aistudio/Anomaly.Paddle
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
Namespace(arch='resnet18', category='leather', img_size=256, k=10, method='coreset', model_path='./output/coreset_resnet18_10/carpet.pdparams', save_dir='./output/coreset_resnet18_10')
W0505 23:11:59.439810  2902 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:11:59.445221  2902 device_context.cc:465] device: 0, cuDNN Version: 7.6.
model resnet18, nParams 2787264
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:77: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  return (isinstance(seq, collections.Sequence) and
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmpzp85lm0v.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmpxdiplums.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmp22pggkiw.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmps33tfdg1.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmpht9nggz5.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmp11b99l2s.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
Model is saved in ./output/coreset_resnet18_10.
登录后复制
       

9 推理

In [4]
%cd /home/aistudio/Anomaly.Paddle/
!python infer.py --model_name='PatchCore' --enable_post_process --use_gpu=True --model_file=output/coreset_resnet18_10/model.pdmodel --input_file=/home/aistudio/data/carpet/test/color/000.png --params_file=output/coreset_resnet18_10/model.pdiparams --category=carpet  --stats=./output/coreset_resnet18_10/stats --save_path=./output/coreset_resnet18_10
登录后复制
       
/home/aistudio/Anomaly.Paddle
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/setuptools/depends.py:2: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
  import imp
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
Inference model(PatchCore)...
load train set feature from: ./output/coreset_resnet18_10/stats
E0506 19:06:01.010391  1895 analysis_config.cc:91] Please compile with gpu to EnableGpu()--- Running analysis [ir_graph_build_pass]--- Running analysis [ir_graph_clean_pass]--- Running analysis [ir_analysis_pass]--- Running IR pass [simplify_with_basic_ops_pass]--- Running IR pass [layer_norm_fuse_pass]---    Fused 0 subgraphs into layer_norm op.--- Running IR pass [attention_lstm_fuse_pass]--- Running IR pass [seqconv_eltadd_relu_fuse_pass]--- Running IR pass [seqpool_cvm_concat_fuse_pass]--- Running IR pass [mul_lstm_fuse_pass]--- Running IR pass [fc_gru_fuse_pass]---    fused 0 pairs of fc gru patterns--- Running IR pass [mul_gru_fuse_pass]--- Running IR pass [seq_concat_fc_fuse_pass]--- Running IR pass [squeeze2_matmul_fuse_pass]--- Running IR pass [reshape2_matmul_fuse_pass]--- Running IR pass [flatten2_matmul_fuse_pass]--- Running IR pass [map_matmul_v2_to_mul_pass]--- Running IR pass [map_matmul_v2_to_matmul_pass]--- Running IR pass [map_matmul_to_mul_pass]--- Running IR pass [fc_fuse_pass]--- Running IR pass [repeated_fc_relu_fuse_pass]--- Running IR pass [squared_mat_sub_fuse_pass]--- Running IR pass [conv_bn_fuse_pass]I0506 19:06:01.055578  1895 fuse_pass_base.cc:57] ---  detected 15 subgraphs--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]--- Running IR pass [conv_transpose_bn_fuse_pass]--- Running IR pass [conv_transpose_eltwiseadd_bn_fuse_pass]--- Running IR pass [is_test_pass]--- Running IR pass [runtime_context_cache_pass]--- Running analysis [ir_params_sync_among_devices_pass]--- Running analysis [adjust_cudnn_workspace_size_pass]--- Running analysis [inference_op_replace_pass]--- Running analysis [memory_optimize_pass]I0506 19:06:01.060403  1895 memory_optimize_pass.cc:216] Cluster name : conv2d_31.tmp_0  size: 262144
I0506 19:06:01.060425  1895 memory_optimize_pass.cc:216] Cluster name : batch_norm_0.tmp_2  size: 4194304
I0506 19:06:01.060428  1895 memory_optimize_pass.cc:216] Cluster name : pool2d_0.tmp_0  size: 1048576
I0506 19:06:01.060431  1895 memory_optimize_pass.cc:216] Cluster name : relu_0.tmp_0  size: 4194304
I0506 19:06:01.060443  1895 memory_optimize_pass.cc:216] Cluster name : conv2d_22.tmp_0  size: 1048576
I0506 19:06:01.060452  1895 memory_optimize_pass.cc:216] Cluster name : x  size: 786432--- Running analysis [ir_graph_to_program_pass]I0506 19:06:01.074777  1895 analysis_predictor.cc:714] ======= optimize end =======
I0506 19:06:01.075248  1895 naive_executor.cc:98] ---  skip [feed], feed -> x
I0506 19:06:01.076575  1895 naive_executor.cc:98] ---  skip [concat_0.tmp_0], fetch -> fetch
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
Inference mode
image_score:[2.66626549]
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2349: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  if isinstance(obj, collections.Iterator):
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:101: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  ret = np.asscalar(ex)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/cbook/__init__.py:2366: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  return list(data) if isinstance(data, collections.MappingView) else data
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:425: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_min = np.asscalar(a_min.astype(scaled_dtype))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/image.py:426: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item() instead
  a_max = np.asscalar(a_max.astype(scaled_dtype))
saved
登录后复制
       

输出结果如下：

10 TIPC

因为test_tipc 不支持后处理的可视化环境，tipc中不进行异常图可视化。

首先安装auto_log，需要进行安装，安装方式如下： auto_log的详细介绍参考https://github.com/LDOUBLEV/AutoLog。

git clone https://github.com/LDOUBLEV/AutoLog
cd AutoLog/
pip3 install -r requirements.txt
python3 setup.py bdist_wheel
pip3 install ./dist/auto_log-1.2.0-py3-none-any.whl
登录后复制
   
In [2]
#%cd /home/aistudio/#!git clone https://github.com/LDOUBLEV/AutoLog%cd /home/aistudio/AutoLog/
!pip3 install -r requirements.txt >/dev/null#!python3 setup.py bdist_wheel!pip3 install ./dist/auto_log-1.2.0-py3-none-any.whl >/dev/null
登录后复制
       
/home/aistudio/AutoLog
登录后复制
       

进行TIPC：

In [11]
%cd /home/aistudio/Anomaly.Paddle/
!bash test_tipc/prepare.sh test_tipc/configs/PatchCore/train_infer_python.txt 'lite_train_lite_infer'
登录后复制
       
/home/aistudio/Anomaly.Paddle
Archive:  MVTec.zip
   creating: MVTec/
  inflating: MVTec/.DS_Store         
   creating: MVTec/capsule/
  inflating: MVTec/capsule/.DS_Store  
   creating: MVTec/capsule/test/
   creating: MVTec/capsule/test/crack/
  inflating: MVTec/capsule/test/crack/001.png  
  inflating: MVTec/capsule/test/crack/000.png  
  inflating: MVTec/capsule/test/.DS_Store  
   creating: MVTec/capsule/test/scratch/
  inflating: MVTec/capsule/test/scratch/001.png  
  inflating: MVTec/capsule/test/scratch/000.png  
  inflating: MVTec/capsule/test/scratch/.DS_Store  
   creating: MVTec/capsule/test/poke/
  inflating: MVTec/capsule/test/poke/001.png  
  inflating: MVTec/capsule/test/poke/000.png  
  inflating: MVTec/capsule/test/poke/.DS_Store  
   creating: MVTec/capsule/test/good/
  inflating: MVTec/capsule/test/good/001.png  
  inflating: MVTec/capsule/test/good/000.png  
  inflating: MVTec/capsule/test/good/.DS_Store  
   creating: MVTec/capsule/test/faulty_imprint/
  inflating: MVTec/capsule/test/faulty_imprint/001.png  
  inflating: MVTec/capsule/test/faulty_imprint/000.png  
  inflating: MVTec/capsule/test/faulty_imprint/.DS_Store  
   creating: MVTec/capsule/test/squeeze/
  inflating: MVTec/capsule/test/squeeze/001.png  
  inflating: MVTec/capsule/test/squeeze/000.png  
  inflating: MVTec/capsule/test/squeeze/.DS_Store  
   creating: MVTec/capsule/ground_truth/
   creating: MVTec/capsule/ground_truth/crack/
  inflating: MVTec/capsule/ground_truth/crack/000_mask.png  
  inflating: MVTec/capsule/ground_truth/crack/001_mask.png  
  inflating: MVTec/capsule/ground_truth/.DS_Store  
   creating: MVTec/capsule/ground_truth/scratch/
  inflating: MVTec/capsule/ground_truth/scratch/000_mask.png  
  inflating: MVTec/capsule/ground_truth/scratch/001_mask.png  
   creating: MVTec/capsule/ground_truth/poke/
  inflating: MVTec/capsule/ground_truth/poke/000_mask.png  
  inflating: MVTec/capsule/ground_truth/poke/001_mask.png  
   creating: MVTec/capsule/ground_truth/faulty_imprint/
  inflating: MVTec/capsule/ground_truth/faulty_imprint/000_mask.png  
  inflating: MVTec/capsule/ground_truth/faulty_imprint/001_mask.png  
   creating: MVTec/capsule/ground_truth/squeeze/
  inflating: MVTec/capsule/ground_truth/squeeze/000_mask.png  
  inflating: MVTec/capsule/ground_truth/squeeze/001_mask.png  
   creating: MVTec/capsule/train/
   creating: MVTec/capsule/train/good/
  inflating: MVTec/capsule/train/good/001.png  
  inflating: MVTec/capsule/train/good/000.png
登录后复制
       
In [12]
%cd /home/aistudio/Anomaly.Paddle/
! bash test_tipc/test_train_inference_python.sh test_tipc/configs/PatchCore/train_infer_python.txt 'lite_train_lite_infer'
登录后复制
       
/home/aistudio/Anomaly.Paddle
Namespace(arch='resnet18', batch_size=32, category='capsule', cpu=False, crop_size=256, data_path='./test_tipc/data/MVTec', debug=False, einsum=False, eval=False, eval_PRO=False, eval_threthold_step=500, inc=False, k=10, load_projection=None, method='coreset', non_partial_AUC=False, num_workers=0, resize=256, save_model=True, save_model_subfolder=False, save_path='./test_tipc/output/PatchCore/', save_pic=False, seed=521, test_batch_size=1)
W0505 23:12:50.398147  3193 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:12:50.403101  3193 device_context.cc:465] device: 0, cuDNN Version: 7.6.
model resnet18, nParams 2787264
Training model 1/1 for capsule
| feature extraction | train | capsule |:   0%|           | 0/1 [00:00<?, ?it/s]/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
| feature extraction | train | capsule |: 100%|███| 1/1 [00:00<00:00,  3.47it/s]
Creating CoreSet Sampler via k-Center Greedy
Getting the coreset from the main embedding.
Assigning the coreset as the memory bank with shape [204, 384].
2022-05-05 23:13:11	Train ends, total 5.96s
Saving model...
2022-05-05 23:13:11	Save model in ./test_tipc/output/PatchCore/capsule.pdparams Run successfully with command - python3.7 train.py --data_path=./test_tipc/data/MVTec --category capsule --method=coreset --arch=resnet18 --k=10 --save_path=./test_tipc/output/PatchCore/ --save_model_subfolder=False --save_pic=False!  /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
Namespace(arch='resnet18', category='leather', img_size=256, k=10, method='coreset', model_path='./test_tipc/output/PatchCore/capsule.pdparams', save_dir='./test_tipc/output/PatchCore/')
W0505 23:13:14.875043  3308 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:13:14.880427  3308 device_context.cc:465] device: 0, cuDNN Version: 7.6.
model resnet18, nParams 2787264
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:77: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  return (isinstance(seq, collections.Sequence) and
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmpeu0e3616.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmphsdl18dg.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmp3pdqc646.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmpcndbd9vo.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmp8vecen64.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:341: UserWarning: /tmp/tmpw8r51_rv.py:21
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
Model is saved in ./test_tipc/output/PatchCore/. Run successfully with command - python3.7 export_model.py --method=coreset --arch=resnet18 --k=10 --model_path=./test_tipc/output/PatchCore/capsule.pdparams --save_dir=./test_tipc/output/PatchCore/!  W0505 23:13:31.946898  3372 analysis_predictor.cc:795] The one-time configuration of analysis predictor failed, which may be due to native predictor called first and its configurations taken effect.--- Running analysis [ir_graph_build_pass]--- Running analysis [ir_graph_clean_pass]--- Running analysis [ir_analysis_pass]--- Running IR pass [is_test_pass]--- Running IR pass [simplify_with_basic_ops_pass]--- Running IR pass [conv_affine_channel_fuse_pass]--- Running IR pass [conv_eltwiseadd_affine_channel_fuse_pass]--- Running IR pass [conv_bn_fuse_pass]I0505 23:13:31.992252  3372 fuse_pass_base.cc:57] ---  detected 15 subgraphs--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]--- Running IR pass [embedding_eltwise_layernorm_fuse_pass]--- Running IR pass [multihead_matmul_fuse_pass_v2]--- Running IR pass [squeeze2_matmul_fuse_pass]--- Running IR pass [reshape2_matmul_fuse_pass]--- Running IR pass [flatten2_matmul_fuse_pass]--- Running IR pass [map_matmul_v2_to_mul_pass]--- Running IR pass [map_matmul_v2_to_matmul_pass]--- Running IR pass [map_matmul_to_mul_pass]--- Running IR pass [fc_fuse_pass]--- Running IR pass [fc_elementwise_layernorm_fuse_pass]--- Running IR pass [conv_elementwise_add_act_fuse_pass]--- Running IR pass [conv_elementwise_add2_act_fuse_pass]--- Running IR pass [conv_elementwise_add_fuse_pass]--- Running IR pass [transpose_flatten_concat_fuse_pass]--- Running IR pass [runtime_context_cache_pass]--- Running analysis [ir_params_sync_among_devices_pass]I0505 23:13:32.002573  3372 ir_params_sync_among_devices_pass.cc:45] Sync params from CPU to GPU--- Running analysis [adjust_cudnn_workspace_size_pass]--- Running analysis [inference_op_replace_pass]--- Running analysis [memory_optimize_pass]I0505 23:13:32.230777  3372 memory_optimize_pass.cc:216] Cluster name : batch_norm_14.tmp_2  size: 262144
I0505 23:13:32.230805  3372 memory_optimize_pass.cc:216] Cluster name : x  size: 786432
I0505 23:13:32.230809  3372 memory_optimize_pass.cc:216] Cluster name : pool2d_0.tmp_0  size: 1048576
I0505 23:13:32.230813  3372 memory_optimize_pass.cc:216] Cluster name : relu_0.tmp_0  size: 4194304
I0505 23:13:32.230816  3372 memory_optimize_pass.cc:216] Cluster name : batch_norm_2.tmp_2  size: 1048576--- Running analysis [ir_graph_to_program_pass]I0505 23:13:32.245414  3372 analysis_predictor.cc:714] ======= optimize end =======
I0505 23:13:32.246016  3372 naive_executor.cc:98] ---  skip [feed], feed -> x
I0505 23:13:32.247359  3372 naive_executor.cc:98] ---  skip [concat_0.tmp_0], fetch -> fetch
W0505 23:13:32.313050  3372 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:13:32.317571  3372 device_context.cc:465] device: 0, cuDNN Version: 7.6.
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
Inference model(PaDiM)...
load train set feature from: ./test_tipc/output/PatchCore/stats Run successfully with command - python3.7 infer.py --stats=./test_tipc/output/PatchCore/stats --use_gpu=True --use_tensorrt=False --precision=fp32 --model_file=./test_tipc/output/PatchCore/model.pdmodel --batch_size=1 --input_file=./test_tipc/data/MVTec/capsule/test/crack/001.png  --params_file=./test_tipc/output/PatchCore/model.pdiparams > ./test_tipc/output/PatchCore/python_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log 2>&1 !  --- Running analysis [ir_graph_build_pass]--- Running analysis [ir_graph_clean_pass]--- Running analysis [ir_analysis_pass]--- Running IR pass [simplify_with_basic_ops_pass]--- Running IR pass [layer_norm_fuse_pass]---    Fused 0 subgraphs into layer_norm op.--- Running IR pass [attention_lstm_fuse_pass]--- Running IR pass [seqconv_eltadd_relu_fuse_pass]--- Running IR pass [seqpool_cvm_concat_fuse_pass]--- Running IR pass [mul_lstm_fuse_pass]--- Running IR pass [fc_gru_fuse_pass]---    fused 0 pairs of fc gru patterns--- Running IR pass [mul_gru_fuse_pass]--- Running IR pass [seq_concat_fc_fuse_pass]--- Running IR pass [squeeze2_matmul_fuse_pass]--- Running IR pass [reshape2_matmul_fuse_pass]--- Running IR pass [flatten2_matmul_fuse_pass]--- Running IR pass [map_matmul_v2_to_mul_pass]--- Running IR pass [map_matmul_v2_to_matmul_pass]--- Running IR pass [map_matmul_to_mul_pass]--- Running IR pass [fc_fuse_pass]--- Running IR pass [repeated_fc_relu_fuse_pass]--- Running IR pass [squared_mat_sub_fuse_pass]--- Running IR pass [conv_bn_fuse_pass]I0505 23:13:44.782842  3435 fuse_pass_base.cc:57] ---  detected 15 subgraphs--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]--- Running IR pass [conv_transpose_bn_fuse_pass]--- Running IR pass [conv_transpose_eltwiseadd_bn_fuse_pass]--- Running IR pass [is_test_pass]--- Running IR pass [runtime_context_cache_pass]--- Running analysis [ir_params_sync_among_devices_pass]--- Running analysis [adjust_cudnn_workspace_size_pass]--- Running analysis [inference_op_replace_pass]--- Running analysis [memory_optimize_pass]I0505 23:13:44.787526  3435 memory_optimize_pass.cc:216] Cluster name : conv2d_31.tmp_0  size: 262144
I0505 23:13:44.787545  3435 memory_optimize_pass.cc:216] Cluster name : batch_norm_0.tmp_2  size: 4194304
I0505 23:13:44.787549  3435 memory_optimize_pass.cc:216] Cluster name : pool2d_0.tmp_0  size: 1048576
I0505 23:13:44.787554  3435 memory_optimize_pass.cc:216] Cluster name : relu_0.tmp_0  size: 4194304
I0505 23:13:44.787556  3435 memory_optimize_pass.cc:216] Cluster name : conv2d_22.tmp_0  size: 1048576
I0505 23:13:44.787559  3435 memory_optimize_pass.cc:216] Cluster name : x  size: 786432--- Running analysis [ir_graph_to_program_pass]I0505 23:13:44.802613  3435 analysis_predictor.cc:714] ======= optimize end =======
I0505 23:13:44.803148  3435 naive_executor.cc:98] ---  skip [feed], feed -> x
I0505 23:13:44.804566  3435 naive_executor.cc:98] ---  skip [concat_0.tmp_0], fetch -> fetch
W0505 23:13:44.870177  3435 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:13:44.874680  3435 device_context.cc:465] device: 0, cuDNN Version: 7.6.
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
Inference model(PaDiM)...
load train set feature from: ./test_tipc/output/PatchCore/stats Run successfully with command - python3.7 infer.py --stats=./test_tipc/output/PatchCore/stats --use_gpu=False --enable_mkldnn=False --cpu_threads=1 --model_file=./test_tipc/output/PatchCore/model.pdmodel --batch_size=1 --input_file=./test_tipc/data/MVTec/capsule/test/crack/001.png   --precision=fp32 --params_file=./test_tipc/output/PatchCore/model.pdiparams > ./test_tipc/output/PatchCore/python_infer_cpu_usemkldnn_False_threads_1_precision_fp32_batchsize_1.log 2>&1 !  --- Running analysis [ir_graph_build_pass]--- Running analysis [ir_graph_clean_pass]--- Running analysis [ir_analysis_pass]--- Running IR pass [simplify_with_basic_ops_pass]--- Running IR pass [layer_norm_fuse_pass]---    Fused 0 subgraphs into layer_norm op.--- Running IR pass [attention_lstm_fuse_pass]--- Running IR pass [seqconv_eltadd_relu_fuse_pass]--- Running IR pass [seqpool_cvm_concat_fuse_pass]--- Running IR pass [mul_lstm_fuse_pass]--- Running IR pass [fc_gru_fuse_pass]---    fused 0 pairs of fc gru patterns--- Running IR pass [mul_gru_fuse_pass]--- Running IR pass [seq_concat_fc_fuse_pass]--- Running IR pass [squeeze2_matmul_fuse_pass]--- Running IR pass [reshape2_matmul_fuse_pass]--- Running IR pass [flatten2_matmul_fuse_pass]--- Running IR pass [map_matmul_v2_to_mul_pass]--- Running IR pass [map_matmul_v2_to_matmul_pass]--- Running IR pass [map_matmul_to_mul_pass]--- Running IR pass [fc_fuse_pass]--- Running IR pass [repeated_fc_relu_fuse_pass]--- Running IR pass [squared_mat_sub_fuse_pass]--- Running IR pass [conv_bn_fuse_pass]I0505 23:13:57.568568  3490 fuse_pass_base.cc:57] ---  detected 15 subgraphs--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]--- Running IR pass [conv_transpose_bn_fuse_pass]--- Running IR pass [conv_transpose_eltwiseadd_bn_fuse_pass]--- Running IR pass [is_test_pass]--- Running IR pass [runtime_context_cache_pass]--- Running analysis [ir_params_sync_among_devices_pass]--- Running analysis [adjust_cudnn_workspace_size_pass]--- Running analysis [inference_op_replace_pass]--- Running analysis [memory_optimize_pass]I0505 23:13:57.573712  3490 memory_optimize_pass.cc:216] Cluster name : conv2d_31.tmp_0  size: 262144
I0505 23:13:57.573740  3490 memory_optimize_pass.cc:216] Cluster name : batch_norm_0.tmp_2  size: 4194304
I0505 23:13:57.573742  3490 memory_optimize_pass.cc:216] Cluster name : pool2d_0.tmp_0  size: 1048576
I0505 23:13:57.573746  3490 memory_optimize_pass.cc:216] Cluster name : relu_0.tmp_0  size: 4194304
I0505 23:13:57.573750  3490 memory_optimize_pass.cc:216] Cluster name : conv2d_22.tmp_0  size: 1048576
I0505 23:13:57.573752  3490 memory_optimize_pass.cc:216] Cluster name : x  size: 786432--- Running analysis [ir_graph_to_program_pass]I0505 23:13:57.589735  3490 analysis_predictor.cc:714] ======= optimize end =======
I0505 23:13:57.590353  3490 naive_executor.cc:98] ---  skip [feed], feed -> x
I0505 23:13:57.591871  3490 naive_executor.cc:98] ---  skip [concat_0.tmp_0], fetch -> fetch
W0505 23:13:57.659296  3490 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0505 23:13:57.663693  3490 device_context.cc:465] device: 0, cuDNN Version: 7.6.
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
  from collections import Sized
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. 
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
Inference model(PaDiM)...
load train set feature from: ./test_tipc/output/PatchCore/stats Run successfully with command - python3.7 infer.py --stats=./test_tipc/output/PatchCore/stats --use_gpu=False --enable_mkldnn=False --cpu_threads=2 --model_file=./test_tipc/output/PatchCore/model.pdmodel --batch_size=1 --input_file=./test_tipc/data/MVTec/capsule/test/crack/001.png   --precision=fp32 --params_file=./test_tipc/output/PatchCore/model.pdiparams > ./test_tipc/output/PatchCore/python_infer_cpu_usemkldnn_False_threads_2_precision_fp32_batchsize_1.log 2>&1 !
登录后复制
       

11 复现心得

cdist运算

利用 broadcast 和 norm 实现 cdist,缺点是目前的 broadcast 机制会成倍消耗显存 使用条件判断适应2d/3d data，说起来没有atleast_nd这种函数还是不太方便

def cdist(X, Y, p=2.0):
    dim = max(len(X.shape), len(Y.shape))    if dim==3:        if len(Y.shape)==2:
            Y = Y.unsqueeze(0)        elif len(Y.shape)==1:
            Y = Y.unsqueeze(0).unsqueeze(0)        else:            assert len(Y.shape)==3
            assert Y.shape[0]=X.shape[0]    #B, P, C = X.shape
    #1|B, R, C = Y.shape
    D = paddle.linalg.norm(X[:, :, None, :]-Y[None, :, :, :], p, axis=-1)    return D
登录后复制
       

减少显存占用的写法：

    def cdist(X, Y, p=2.0):
    #2d P, C = X.shape| R, C = Y.shape -> P,R
    P, C = X.shape
    R, C = Y.shape 
    #3d B, P, C = X.shape|1, R, C = Y.shape -> B, P,R
    #D = paddle.linalg.norm(X[:, None, :]-Y[None, :, :], axis=-1)
    D = paddle.zeros((P, R))    for i in range(P):
        D[i,:] = paddle.linalg.norm(X[i, None, :]-Y, axis=-1)        #D[i,:] = (X[i, None, :]-Y).square().sum(-1).sqrt_()
    return D
登录后复制
       

希望paddle Hackathon 能够早点补上原生实现(https://github.com/PaddlePaddle/community/blob/master/rfcs/APIs/20220316_api_design_for_cdist.md)

Avgpool2D 默认表现与pytorch不一致

paddle.nn.AvgPool2D 默认exclusive=True, 与pytorch对应的参数为exclusive=False

以上就是【论文复现】PatchCore: 面向全召回率的工业异常检测的详细内容，更多请关注php中文网其它相关文章！

相关标签：
python git ai 百度 red igs asic padding github 算法 pytorch paddlepaddle https

大家都在看：

最佳 Windows 性能的顶级免费优化软件
最佳 Windows 性能的顶级免费优化软件

每个人都需要一台速度更快、更稳定的 PC。随着时间的推移，垃圾文件、旧注册表数据和不必要的后台进程会占用资源并降低性能。幸运的是，许多工具可以让 Windows 保持平稳运行。

下载
来源：php中文网
收藏 点赞
上一篇：RNN(LSTM&GRU)文本分类（PaddlePaddle2.0） 下一篇：【飞桨学习赛：遥感影像地块分割】22年7月第一名方案
本文内容由网友自发贡献，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系admin@php.cn
作者最新文章
最新问题
豆包AI互动搜索入口在哪里 豆包AI查询聊天网页版链接 豆包AI互动搜索入口在官网https://www.doubao.com/chat/，用户可通过网页版直接登录使用，支持文本对话、文档阅读、网页速读和多语种翻译等功能，操作便捷且基于云雀大模型提供高效智能服务。
2025-11-06 14:45:18
669
即梦4.0如何使用智能对象识别_即梦4.0自动识别图中元素并优化功能教程 即梦4.0可通过智能对象识别自动优化图像，1、打开应用并导入图片，点击AI识别图标启动扫描；2、系统用彩色轮廓标记人物、建筑等对象，支持手动添加或删除识别区域；3、点击“一键优化”按语义类型调整各元素，如增强人像肤色、提升天空饱和度；4、可导出JM-Layer格式文件，保留识别信息与优化参数用于后续编辑。
2025-11-06 14:42:02
279
百度AI搜索使用指南 附百度AI搜索官方免登录入口 百度AI搜索官方免登录入口是https://chat.baidu.com/，用户可直接访问该网址使用其文生文、智能摘要、多模态交互及@智能体等功能，无需注册即可体验多设备同步的免费服务。
2025-11-06 14:38:02
685
讯飞火星AI如何进行亲子教育对话辅助_讯飞火星AI亲子沟通与教育建议生成方法 讯飞火星AI通过启用亲子教育模式、实时对话建议、行为记录分析、模拟训练及家庭协同支持，帮助家长提升沟通技巧与教育策略。首先开启“家庭教育”场景并激活辅助功能，系统将优化语言表达；在对话中，AI实时识别情绪与压力话题，提供三条科学回应建议；长期保存互动日志可生成weekly沟通质量报告，并推荐个性化改进任务；家长还可通过模拟训练模块练习应对不同年龄段孩子的典型问题；最后，多成员绑定账户实现育儿语言统一，确保教育一致性，全面提升亲子教育质量。
2025-11-06 14:25:02
748
DeepSeek AI生图入口 DeepSeek AI生成PPT免费入口 DeepSeekAI生图与PPT生成入口在官网https://www.deepseek.com，登录后选择“文生图”或“文档生成”功能，按步骤输入描述、设置参数并导出结果，支持多端同步与智能优化。
2025-11-06 14:00:02
949
通义千问官方主页访问地址 通义千问平台智能对话官网直达链接 通义千问官方主页访问地址是https://tongyi.aliyun.com/qianwen/，用户可通过网页端或下载“通义”App跨设备使用，支持多模态交互与AI生视频等功能。
2025-11-06 13:50:02
252
DeepSeekOCR怎么识别日文内容_DeepSeekOCR日文文字识别功能与使用方法 要实现高效日文文字识别，需正确配置语言模型并优化图像质量。一、启用日文语言模型：调用OCR接口时设置language参数为"ja"，PythonSDK示例为result=deepseek_ocr.recognize(image_path,language=‘ja’)，API请求需在JSON中包含"language":"ja"。二、优化图像预处理：转换为灰度图、分辨率提升至300dpi以上、使用锐化滤镜、校正倾斜及裁剪无关区域。三、使用批量识别模式：将多页日文图像放入同一文件夹，通过脚本调用批量功
2025-11-06 13:49:13
790
ai搜题在线官方网页入口_ai搜题人工智能搜题平台主页入口 AI搜题在线官方网页入口为https://aishouti.example.edu.cn，平台支持多学科题目识别、图片或文字搜题、相似题推荐及知识点关联，具备简洁界面、快速响应、移动端适配和历史记录保存等优化体验，集成公式编辑器、错题本、学习进度追踪和个性化训练功能。
2025-11-06 13:42:02
611
即梦无法登录是什么原因_即梦登录异常原因解析 先检查网络连接，确认账号密码正确，清除浏览器缓存或更换设备尝试，查看服务器是否维护，最后联系客服获取帮助。
2025-11-06 13:32:02
720
AI视频人物动作捕捉怎么实现_人物动作捕捉AI技术应用与操作指南 AI动作捕捉技术可将静态图像或视频中的人物转化为3D动画角色。首先，使用Cyanpuppets等AI软件通过摄像头或视频提取人体2D/3D关键点，生成骨骼运动并导出为FBX格式用于Blender或UnrealEngine。其次，利用LivePortrait等工具进行面部表情捕捉，通过源图像与驱动视频实现微笑、眨眼等微表情动画。接着，在UnrealEngine中安装CyanSDK等插件，结合RGB摄像头实时驱动MetaHuman角色，需配备8GB显存以上显卡。最后，通过Blender搭配DiMoc
2025-11-06 13:24:03
876
相关专题
更多>
热门推荐
开源免费商场系统广告
热门教程
更多>
相关推荐
热门推荐
最新课程
最新下载
更多>
网站特效
网站源码
网站素材
前端模板
关于我们 免责申明 意见反馈 讲师合作 广告合作 最新更新 English
php中文网：公益在线php培训，帮助PHP学习者快速成长！
关注服务号 技术交流群
PHP中文网订阅号
每天精选资源文章推送
PHP中文网APP
随时随地碎片化学习

Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号

  • PHP学习

  • 技术支持

  • 返回顶部