tensorflow python framework erros invalidArgmentError

问题描述

tensorflow python framework erros invalidArgmentError:connot batch tensors with different shapes in componet 0. First element had shape [227,227,3] and element 19 had shape [227,227,4]
解决办法：数据集图像格式不对；convert(‘RGB’)

解决代码：

import numpy as np
from PIL import Image
import os
import cv2

directory_name='./flower_data/flower_photos/321'


for filename in os.listdir(directory_name):
    '''
	# 用os库读取文件夹内所有图片名称以操作
    img1 = cv2.imread(directory_name + "/" + filename)
    # print(filename)
    c = img1.shape[2]
    if c == 1:
        print('*'+filename)
    # img = Image.open(directory_name + "/" + filename)
    img2 = img1[:, :, ::-1]
    cv2.imwrite('./flower_data_rgb/flower_photos/321/{}'.format(filename), img2)
    '''

    '''
    b,g,r=cv2.split(img)
    img2=cv2.merge([r.g.b])
    '''
    img = Image.open(directory_name+'/'+filename)
    if (img.mode != 'RGB'):
        img = img.convert('RGB')

    img.save('./flower_data_rgb/flower_photos/321/{}'.format(filename))

参考文章：https://blog.csdn.net/m0_37712157/article/details/87102507
代码部分找不到参考了部分大佬，找不到链接了 ，不过还是表示感谢。

其中，注释掉部分代码采用的使cv2转换成RGB ，转换成之后图像背景会出现变色，变黄或者变红，暂时为找到原因。因此注掉了。