小编Joe*_*boy的帖子

我正在尝试制作 CNN（仍然是初学者）。尝试拟合模型时，出现此错误：

ValueError: 一个形状为 (10000, 10) 的目标数组被传递给形状 (None, 6, 6, 10) 的输出，同时用作 loss categorical_crossentropy。此损失期望目标与输出具有相同的形状。

标签的形状 = (10000, 10) 图像数据的形状 = (10000, 32, 32, 3)

代码：

import pickle
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import (Dense, Dropout, Activation, Flatten, 
                                     Conv2D, MaxPooling2D)
from tensorflow.keras.callbacks import TensorBoard
from keras.utils import to_categorical
import numpy as np
import time

MODEL_NAME = f"_________{int(time.time())}"
BATCH_SIZE = 64

class ConvolutionalNetwork():
    '''
    A convolutional neural network to be used to classify images
    from the …

尝试收集我的静态文件，因为我很快就会部署我的网站。接收：

Unknown command: 'collectstatic'

检查 django-admin 帮助后，我收到此警告：

(error: Requested setting INSTALLED_APPS, but settings are not configured. 
 You must either define the environment variable DJANGO_SETTINGS_MODULE or call 
 settings.configure() before accessing settings.).

这是我的manage.py：

def main():
    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'xwordsite.settings')
    try:
        from django.core.management import execute_from_command_line
    except ImportError as exc:
        raise ImportError(
            "Couldn't import Django. Are you sure it's installed and "
            "available on your PYTHONPATH environment variable? Did you "
            "forget to activate a virtual environment?"
        ) from exc
    execute_from_command_line(sys.argv)

我尝试运行manage.py shell，但没有解决问题。我也不确定这是否重要，但我所有的静态文件都在项目目录中。还有静态设置：

STATIC_URL = '/static/' …