我无法训练张量流答案

【问题标题】：I cannot train tensorflow我无法训练张量流
【发布时间】：2022-04-29 07:56:02
【问题描述】：

我正在尝试按照这些说明来训练 tensorflow： https://www.datacamp.com/community/tutorials/tensorflow-tutorial?utm_source=adwords_ppc&utm_campaignid=898687156&utm_adgroupid=48947256715&utm_device=c&utm_keyword=&utm_matchtype=b&utm_network=g&utm_adpostion=1t1&utm_creative=255798340456&utm_targetid=dsa-498578051924&utm_loc_interest_ms=&utm_loc_physical_ms=9061578&gclid=Cj0KCQiA5dPuBRCrARIsAJL7oeh8O1BawcnisHgACgu2gxP1BcofUPxNxsMf2D7cOjC-7QYeuU3ZBZEaAuDnEALw_wcB

我执行这段代码：

import os
import numpy as np

def load_data(data_directory):
    directories = [d for d in os.listdir(data_directory)
            if os.path.isdir(os.path.join(data_directory, d))]

    labels = []
    images = []
    for d in directories:
        label_directory = os.path.join(data_directory,d)
        file_names = [os.path.join(label_directory, f)
                for f in os.listdir(label_directory)
                if f.endswith(".ppm")]
        for f in file_names:
            images.append(skimage.data.imread(f))
            labels.append(int(d))
    return images, labels

ROOT_PATH = "/home/"
train_data_directory = os.path.join(ROOT_PATH, "BelgiumTSC_Training/Training")
test_data_directory = os.path.join(ROOT_PATH, "BelgiumTSC_Testing/Testing")

images, labels = load_data(train_data_directory)

# print the 'images' dimensions
print(np.array(images).ndim)

# print the number of 'images''s elements
print(np.array(images).size)

# print the first instance of 'images'
images[0]

我收到此错误：

Traceback (most recent call last):
  File "loading_data.py", line 24, in <module>
    images, labels = load_data(train_data_directory)
  File "loading_data.py", line 16, in load_data
    images.append(skimage.data.imread(f))
NameError: name 'skimage' is not defined

我点击了这个链接但没有成功： Import error No module named skimage

【问题讨论】：

看来您需要导入scikit-image 和import skimage。如果scikit-image没有安装，可以用pip或者conda安装（见scikit-image.org/docs/stable/install.html）
我做了import skimage 现在我得到：Traceback (most recent call last): File "loading_data.py", line 25, in <module> images, labels = load_data(train_data_directory) File "loading_data.py", line 17, in load_data images.append(skimage.data.imread(f)) AttributeError: module 'skimage.data' has no attribute 'imread'
是skimage.io.imread，教程可能有错别字。
因为我很新，所以tensorflow是我只用输入图片训练的DNN吗？我可以配置它吗？我可以在张量流中改变什么？例如，我可以配置内部阶段及其神经元的权重吗？
1 4575 Traceback (most recent call last): File "loading_data.py", line 38, in <module> print(labels.ndim) AttributeError: 'list' object has no attribute 'ndim' 这是什么错误？

标签： python scikit-learn scikit-image

【解决方案1】：

而不是

images.append(skimage.data.imread(f))

使用

import cv2
images.append(cv2.imread(f))

【讨论】：