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☜☜☜
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。
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
/home/aistudio/data
4 依赖安装
In [1]
!pip install scikit-image >/dev/null
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.
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
/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
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
/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
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
/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
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
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
/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
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
/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.
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
/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
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
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
/home/aistudio/AutoLog
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'
/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
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'
/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 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 !
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
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
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
