写入hdf5文件的时候TypeError: Can't broadcast (1000,) -> (1000, 64, 64, 3)

######在跑《deep learning for computer vision with python》第二本第11章的tiny-imagenet200t程序时候，写入hdf5文件的时候，训练集可以正常写入，但是到验证集的时候报错。TypeError: Can't broadcast (1000,) -> (1000, 64, 64, 3)

# import the necessary packages
import sys
import os

BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(BASE_DIR)
from config import tiny_imagenet_config as config
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from pyimagesearch.io import HDF5DatasetWriter
from imutils import paths
import numpy as np
import progressbar
import json
import cv2
import os

# grab the paths to the training images, then extract the training
# class labels and encode them
trainPaths = list(paths.list_images(config.TRAIN_IMAGES))
trainLabels = [p.split(os.path.sep)[-3] for p in trainPaths]
le = LabelEncoder()
trainLabels = le.fit_transform(trainLabels)

# perform stratified sampling from the training set to construct a
# a testing set
split = train_test_split(trainPaths, trainLabels, test_size=config.NUM_TEST_IMAGES, stratify=trainLabels,
                         random_state=42)
(trainPaths, testPaths, trainLabels, testLabels) = split

# load the validation filename => class from file and then use these
# mappings to build the validation paths and label lists
M = open(config.VAL_MAPPINGS).read().strip().split("\n")
M = [r.split("\t")[:2] for r in M]
valPaths = [os.path.sep.join([config.VAL_IMAGES, m[0]]) for m in M]
valLabels = le.transform([m[1] for m in M])

# construct a list pairing the training, validation, and testing
# image paths along with their corresponding labels and output HDF5
# files
datasets = [
    ("train", trainPaths, trainLabels, config.TRAIN_HDF5),
    ("val", valPaths, valLabels, config.VAL_HDF5),
    ("test", testPaths, testLabels, config.TEST_HDF5)]

# initialize the lists of RGB channel averages
(R, G, B) = ([], [], [])

# loop over the dataset tuples
for (dType, paths, labels, outputPath) in datasets:
    # create HDF5 writer
    print("[INFO] building {}...".format(outputPath))
    writer = HDF5DatasetWriter((len(paths), 64, 64, 3), outputPath)
    # initialize the progress bar
    widgets = ["Building Dataset: ", progressbar.Percentage(), " ", progressbar.Bar(), " ", progressbar.ETA()]
    pbar = progressbar.ProgressBar(maxval=len(paths), widgets=widgets).start()

    # loop over the image paths
    for (i, (path, label)) in enumerate(zip(paths, labels)):
        # load the image from disk
        image = cv2.imread(path)

        # if we are building the training dataset, then compute the
        # mean of each channel in the image, then update the
        # respective lists
        if dType == "train":
            (b, g, r) = cv2.mean(image)[:3]
            R.append(r)
            G.append(g)
            B.append(b)

        # add the image and label to the HDF5 dataset
        writer.add([image], [label])
        pbar.update(i)

    # close the HDF5 writer
    pbar.finish()
    writer.close()

# construct a dictionary of averages, then serialize the means to a
# JSON file
print("[INFO] serializing means...")
D = {"R": np.mean(R), "G": np.mean(G), "B": np.mean(B)}
f = open(config.DATASET_MEAN, "w")
f.write(json.dumps(D))
f.close()

参考
https://blog.csdn.net/qq_41813258/article/details/101453464

事实上是题主的验证集数据出现了问题，一维数据不能扩散到4维，我猜这个数据大概率是错误数据，具体可以在入库之前打印看是否有问题，解决方案可以考虑过滤或者跟代码为什么会出错，以及可以参考：