模型训练在 1 个周期后失败

问题描述 投票:0回答:1

我是Python新手,需要在数据集上训练模型。我在同一位置找到了笔记本和数据集,并对笔记本进行了适当的更改以运行存储中的数据。代码在1后的训练阶段失败纪元以“图形执行错误”完成

这是我的 jupyter 笔记本:https://github.com/Megahedron69/wasteSegregationmodel

这是数据集:https://www.kaggle.com/datasets/aashidutt3/waste-segregation-image-dataset

这是原始笔记本:https://www.kaggle.com/code/gpiosenka/waste-f1-score-97

笔记本中的具体错误位置:

整个错误:

python tensorflow keras kaggle
1个回答
0
投票

感谢@Dr.史努比答案。我的数据集中有损坏的图像,因此在我的根目录中使用了一个简单的 python 脚本来删除截断的图像

#pip install pillow
from PIL import Image
import os

def find_truncated_images(dataset_dir):
    truncated_images = []
    for root, _, files in os.walk(dataset_dir):
        for filename in files:
            file_path = os.path.join(root, filename)
            try:
                with Image.open(file_path) as img:
                    img.load()
            except (IOError, OSError) as e:
                # Log the file path if it's a truncated image
                print(f"Truncated image: {file_path}")
                truncated_images.append(file_path)
    return truncated_images

def remove_truncated_images(truncated_images):
    for file_path in truncated_images:
        try:
            os.remove(file_path)
            print(f"Removed: {file_path}")
        except OSError as e:
            print(f"Error removing {file_path}: {e}")

if __name__ == "__main__":
    dataset_dir = "."  # Set the path to your dataset directory
    truncated_images = find_truncated_images(dataset_dir)
    remove_truncated_images(truncated_images)
© www.soinside.com 2019 - 2024. All rights reserved.