私的AI研究会 > PyReview3
坂本俊之著「PyTorch ではじめる AI開発」をもとに AI学習を復習。
CHAPTER 03 「教師データにない状況を異常検出」異常検出を行う AI を作成する。
(base) PS > conda activate py_learn (py_learn) PS > cd /anaconda_win/workspace_pylearn/chapter02Linux の場合
(base) $ conda activate py_learn (py_learn) $ cd ~/workspace_pylearn/chapter02
(py_learn) mkdir unnormal-validations (py_learn) ffmpeg -i ../sample/chapt03/chapt03-validate.mp4 -f image2 unnormal-validations/%03d.jpg
(py_learn) PS > python chapt03_1x.py learning start >> 2024-03-10 11:22:31.219226 epoch #0: train_loss:0.7922095060348511 epoch #1: train_loss:0.023104708641767502 epoch #2: train_loss:0.018580107018351555 learning end >> 2024-03-10 11:28:41.251456 learning time >> 0:06:10.032654
(py_learn) $ python chapt03_1x.py learning start >> 2024-03-10 13:29:56.149561 epoch #0: train_loss:0.8014032244682312 epoch #1: train_loss:0.023702777922153473 epoch #2: train_loss:0.01885644905269146 learning end >> 2024-03-10 13:39:35.513480 learning time >> 0:09:39.363922
OS | 機種 | 開始日時 | 終了日時 | 処理時間 (h:m) |
Windows11 | HP ENVY TE02-1097 NVIDIA GeForce RTX 4070 Ti | 2024/03/10 11:22 | 2024/03/10 11:28 | 00:06 |
UIbuntu22.04LTS | HP ENVY TE02-1097 NVIDIA GeForce RTX 4070 Ti | 2024/03/10 13:29 | 2024/03/10 13:39 | 00:09 |
Windows10 | HP EliteDesk 800 NVIDIA GeForce GTX 1050 Ti | 2024/03/10 13:45 | 2024/03/10 16:10 | 02:24 |
Windows11 | DELL XPS Plus 9320 Intel® Core™ i7-1260P CPU | 2024/03/03 11:10 | 2024/03/03 14:48 | 03:38 |
Ubuntu20.04LTS | DELL Latitude 7520 Intel® Core™ i7-1185G7 CPU | 2024/03/05 10:24 | 2024/03/05 14:41 | 04:17 |
Windows10 | HP EliteDesk 800 Intel® Core™ i7-6700 CPU | 2024/03/07 16:10 | 2024/03/07 22:56 | 06:45 |
-a---- 2024/03/03 14:44 94413070 chapt03-model1.pth -a---- 2024/03/03 14:48 345 chapt03-normal.json -a---- 2024/03/03 14:48 58163 scatter.png
(py_learn) python chapt03_2x.py
(py_learn) python chapt03_2y.py --- Surveillance camera Abnormality monitoring --- 4.9.0 Surveillance camera Abnormality monitoring: Starting application... - Image File : ../sample/chapt03/chapt03-sample-a.mp4 - Language : jp - Program Title: y - Speed flag : y - Processed out: non FPS average: 12.30 Finished.
(py_learn) PS > python chapt03_1x.py C:\anaconda_win\workspace_pylearn\chapter02\chapt03_1x.py:13: DeprecationWarning: Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0), (to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries) but was not found to be installed on your system. If this would cause problems for you, please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466 import pandas as pd :
(py_learn) > pip install pyarrow