从文件创建分类清单CSV文件

从文件创建清单CSV文件

1. 创建每行包含以下字段的CSV文件（每张图像一行）。不要在CSV文件中添加标题行。

   字段 1	字段 2
   图像名称或图像的 Amazon S3 路径。例如，s3://s3bucket/circuitboard/train/anomaly/train-anomaly_10.jpg。您不能混合使用带有 Amazon S3 路径的图像和不带 Amazon S3 路径的图像。	图像的异常分类（normal 或 anomaly）。

   例如，s3://s3bucket/circuitboard/train/anomaly/image_10.jpg,anomaly 或 image_11.jpg,normal

2. 保存 CSV 文件。

3. 运行以下 Python 脚本。提供以下参数：

   • csv_file— 您在步骤 1 中创建的CSV文件。

   • （可选）--s3-path s3://path_to_folder/：要添加到图像文件名（字段 1）的 Amazon S3 路径。如果字段 1 中的图像未包含 S3 路径，则使用 --s3-path。

   # Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
   # SPDX-License-Identifier:  Apache-2.0
   """
   Purpose
   Shows how to create an Amazon Lookout for Vision manifest file from a CSV file.
   The CSV file format is image location,anomaly classification (normal or anomaly)
   For example:
   s3://s3bucket/circuitboard/train/anomaly/train_11.jpg,anomaly
   s3://s3bucket/circuitboard/train/normal/train_1.jpg,normal
   
   If necessary, use the bucket argument to specify the Amazon S3 bucket folder for the images.
   """
   
   from datetime import datetime, timezone
   import argparse
   import logging
   import csv
   import os
   import json
   
   logger = logging.getLogger(__name__)
   
   
   def check_errors(csv_file):
       """
       Checks for duplicate images and incorrect classifications in a CSV file.
       If duplicate images or invalid anomaly assignments are found, an errors CSV file
       and deduplicated CSV file are created. Only the first
       occurrence of a duplicate is recorded. Other duplicates are recorded in the errors file.
       :param csv_file: The source CSV file
       :return: True if errors or duplicates are found, otherwise false.
       """
   
       logger.info("Checking %s.", csv_file)
   
       errors_found = False
       errors_file = f"{os.path.splitext(csv_file)[0]}_errors.csv"
       deduplicated_file = f"{os.path.splitext(csv_file)[0]}_deduplicated.csv"
   
       with open(csv_file, 'r', encoding="UTF-8") as input_file,\
               open(deduplicated_file, 'w', encoding="UTF-8") as dedup,\
               open(errors_file, 'w', encoding="UTF-8") as errors:
   
           reader = csv.reader(input_file, delimiter=',')
           dedup_writer = csv.writer(dedup)
           error_writer = csv.writer(errors)
           line = 1
           entries = set()
           for row in reader:
   
               # Skip empty lines.
               if not ''.join(row).strip():
                   continue
   
               # Record any incorrect classifications.
               if not row[1].lower() == "normal" and not row[1].lower() == "anomaly":
                   error_writer.writerow(
                       [line, row[0], row[1], "INVALID_CLASSIFICATION"])
                   errors_found = True
   
               # Write first image entry to dedup file and record duplicates.
               key = row[0]
               if key not in entries:
                   dedup_writer.writerow(row)
                   entries.add(key)
               else:
                   error_writer.writerow([line, row[0], row[1], "DUPLICATE"])
                   errors_found = True
               line += 1
   
       if errors_found:
           logger.info("Errors found check %s.", errors_file)
       else:
           os.remove(errors_file)
           os.remove(deduplicated_file)
   
       return errors_found
   
   
   def create_manifest_file(csv_file, manifest_file, s3_path):
       """
       Read a CSV file and create an Amazon Lookout for Vision classification manifest file.
       :param csv_file: The source CSV file.
       :param manifest_file: The name of the manifest file to create.
       :param s3_path: The Amazon S3 path to the folder that contains the images.
       """
       logger.info("Processing CSV file %s.", csv_file)
   
       image_count = 0
       anomalous_count = 0
   
       with open(csv_file, newline='', encoding="UTF-8") as csvfile,\
           open(manifest_file, "w", encoding="UTF-8") as output_file:
   
           image_classifications = csv.reader(
               csvfile, delimiter=',', quotechar='|')
   
           # Process each row (image) in the CSV file.
           for row in image_classifications:
               # Skip empty lines.
               if not ''.join(row).strip():
                   continue
   
               source_ref = str(s3_path) + row[0]
               classification = 0
   
               if row[1].lower() == 'anomaly':
                   classification = 1
                   anomalous_count += 1
   
              # Create the JSON line.
               json_line = {}
               json_line['source-ref'] = source_ref
               json_line['anomaly-label'] = str(classification)
   
               metadata = {}
               metadata['confidence'] = 1
               metadata['job-name'] = "labeling-job/anomaly-classification"
               metadata['class-name'] = row[1]
               metadata['human-annotated'] = "yes"
               metadata['creation-date'] = datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%S.%f')
               metadata['type'] = "groundtruth/image-classification"
   
               json_line['anomaly-label-metadata'] = metadata
   
               output_file.write(json.dumps(json_line))
               output_file.write('\n')
               image_count += 1
   
       logger.info("Finished creating manifest file %s.\n"
                   "Images: %s\nAnomalous: %s",
                   manifest_file,
                   image_count,
                   anomalous_count)
       return image_count, anomalous_count
   
   
   def add_arguments(parser):
       """
       Add command line arguments to the parser.
       :param parser: The command line parser.
       """
   
       parser.add_argument(
           "csv_file", help="The CSV file that you want to process."
       )
   
       parser.add_argument(
           "--s3_path", help="The Amazon S3 bucket and folder path for the images."
           " If not supplied, column 1 is assumed to include the Amazon S3 path.", required=False
       )
   
   
   def main():
   
       logging.basicConfig(level=logging.INFO,
                           format="%(levelname)s: %(message)s")
   
       try:
   
           # Get command line arguments.
           parser = argparse.ArgumentParser(usage=argparse.SUPPRESS)
           add_arguments(parser)
           args = parser.parse_args()
           s3_path = args.s3_path
           if s3_path is None:
               s3_path = ""
   
           csv_file = args.csv_file
           csv_file_no_extension = os.path.splitext(csv_file)[0]
           manifest_file = csv_file_no_extension + '.manifest'
   
           # Create manifest file if there are no duplicate images.
           if check_errors(csv_file):
               print(f"Issues found. Use {csv_file_no_extension}_errors.csv "\
                   "to view duplicates and errors.")
               print(f"{csv_file}_deduplicated.csv contains the first"\
                   "occurrence of a duplicate.\n"
                     "Update as necessary with the correct information.")
               print(f"Re-run the script with {csv_file_no_extension}_deduplicated.csv")
           else:
               print('No duplicates found. Creating manifest file.')
   
               image_count, anomalous_count = create_manifest_file(csv_file, manifest_file, s3_path)
   
               print(f"Finished creating manifest file: {manifest_file} \n")
   
               normal_count = image_count-anomalous_count
               print(f"Images processed: {image_count}")
               print(f"Normal: {normal_count}")
               print(f"Anomalous: {anomalous_count}")
   
       except FileNotFoundError as err:
           logger.exception("File not found.:%s", err)
           print(f"File not found: {err}. Check your input CSV file.")
   
   if __name__ == "__main__":
       main()
   
   

4. 如果出现重复的图像或出现分类错误：

   1. 使用错误文件更新经过重复数据删除CSV的文件或输入文件。CSV

   2. 使用已删除重复数据的更新CSV文件或更新的输入CSV文件再次运行脚本。

5. 如果您计划使用测试数据集，请重复步骤 1-4，以便为测试数据集创建清单文件。

6. 如有必要，请将图像从您的计算机复制到您在CSV文件第 1 列中指定的（或在--s3-path命令行中指定）的 Amazon S3 存储桶路径。要复制图像，请在命令提示符处输入以下命令。

   aws s3 cp --recursive your-local-folder/ s3://your-target-S3-location/

7. 按照 使用清单文件创建数据集（控制台） 部分的说明操作，创建一个数据集。如果您使用的是 AWS SDK，请参阅使用清单文件创建数据集 (SDK)。