遇到错误" ValueError: Shapes (None, 5) and (None, 4) are incompatible"

Question

任何人都能帮我解决这个错误吗？文件总数为2204到5个类。以及1764个用于训练的文件。提前感谢。

这是我的代码：

import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.python.keras.layers import Dense, Flatten
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
import pathlib
data_dir = r"/root/data_Camera"
data_dir = pathlib.Path(data_dir)
rock = list(data_dir.glob('rock/*'))
print(rock[0])
PIL.Image.open(str(rock[0]))
img_height, img_width = 400,2000
batch_size = 32
trains_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split = 0.2,
subset = "training",
seed = 123,
label_mode = 'categorical',
image_size = (img_height, img_width),
batch_size = batch_size)
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=123,
label_mode = 'categorical',
image_size=(img_height, img_width),
batch_size=batch_size)
class_names = trains_ds.class_names
print(class_names)
resnet_model = Sequential()
pretrained_model = tf.keras.applications.ResNet50(include_top=False, 
input_shape=(400,2000,3),
pooling='avg', 
classes = 5, 
weights = 'imagenet')
for layer in pretrained_model.layers: 
layer.trainable=False
resnet_model.add(pretrained_model)
resnet_model.add(Flatten())
resnet_model.add(Dense(512, activation='relu'))
resnet_model.add(Dense(4,activation='softmax'))
resnet_model.summary()
resnet_model.compile(optimizer=Adam(learning_rate=0.001),loss='categorical_crossentropy',metrics=['accuracy'])
epochs = 10
history= resnet_model.fit(
trains_ds,
validation_data=val_ds,
epochs=epochs)

而我遇到的错误是：ValueError:形状(无，5(和(无，4(不兼容我还将文件代码添加到此处。https://github.com/CallaDai/Tensorflow.git你可以去看看。非常感谢。

Answer 1

最近遇到了类似的问题，请考虑使用loss='sparse_categorical_crossentropy而不是loss='categorical_crossentropy。出现此错误的原因可能是"categorical_crossentry"适用于一个热编码目标，而"sparse_categorical_ccrossentry"适用于整数目标。