它是logits形状和分类不匹配，你需要选择100个具有不同形状的目标类，并将其形成为（100，0）或等价物。
样本：相同的输入类型的期望或其中比较，损失函数和统计矩阵计算从估计和评估的步骤相同的输入或不同的输入。RMS可以使用任何仍然正确，但你需要使估计量的范围。

import tensorflow as tf

import os
from os.path import exists

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
None
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
physical_devices = tf.config.experimental.list_physical_devices('GPU')
assert len(physical_devices) > 0, "Not enough GPU hardware devices available"
config = tf.config.experimental.set_memory_growth(physical_devices[0], True)
print(physical_devices)
print(config)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Variables
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
class_100_names = ['apple', 'aquarium_fish', 'baby', 'bear', 'beaver', 
'bed', 'bee', 'beetle', 'bicycle', 'bottle', 
'bowl', 'boy', 'bridge', 'bus', 'butterfly', 
'camel', 'can', 'castle', 'caterpillar', 
'cattle', 'chair', 'chimpanzee', 'clock', 'cloud', 
'cockroach', 'couch', 'crab', 'crocodile', 'cup', 
'dinosaur', 'dolphin', 'elephant', 'flatfish', 'forest', 
'fox', 'girl', 'hamster', 'house', 'kangaroo', 
'keyboard', 'lamp', 'lawn_mower', 'leopard', 'lion', 
'lizard', 'lobster', 'man', 'maple_tree', 'motorcycle', 
'mountain', 'mouse', 'mushroom', 'oak_tree', 'orange', 
'orchid', 'otter', 'palm_tree', 'pear', 'pickup_truck', 
'pine_tree', 'plain', 'plate', 'poppy', 'porcupine', 
'possum', 'rabbit', 'raccoon', 'ray', 'road', 
'rocket', 'rose', 'sea', 'seal', 'shark', 
'shrew', 'skunk', 'skyscraper', 'snail', 'snake', 
'spider', 'squirrel', 'streetcar', 'sunflower', 'sweet_pepper', 
'table', 'tank', 'telephone', 'television', 'tiger', 
'tractor', 'train', 'trout', 'tulip', 'turtle', 
'wardrobe', 'whale', 'willow_tree', 'wolf', 'woman', 'worm'] 

checkpoint_path = "F:\\models\\checkpoint\\" + os.path.basename(__file__).split('.')[0] + "\\TF_DataSets_01.h5"
checkpoint_dir = os.path.dirname(checkpoint_path)

if not exists(checkpoint_dir) : 
    os.mkdir(checkpoint_dir)
    print("Create directory: " + checkpoint_dir)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Dataset
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.cifar100.load_data(label_mode='fine')

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Initialize
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
model = tf.keras.models.Sequential([
    tf.keras.layers.InputLayer(input_shape=( 32, 32, 3 )),
    tf.keras.layers.Normalization(mean=3., variance=2.),
    tf.keras.layers.Normalization(mean=4., variance=6.),
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Reshape((128, 225)),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(96, return_sequences=True, return_state=False)),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(96)),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(192, activation='relu'),
    tf.keras.layers.Dense(100),
])

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Callback
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
class custom_callback(tf.keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs={}):
        if( logs['accuracy'] >= 0.95 ):
            self.model.stop_training = True
    
custom_callback = custom_callback()

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Optimizer
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
optimizer = tf.keras.optimizers.RMSprop(
    learning_rate=0.001,
    rho=0.9,
    momentum=0.0,
    epsilon=1e-07,
    centered=False,
    # decay=None,           # {'lr', 'global_clipnorm', 'clipnorm', 'decay', 'clipvalue'}
    # clipnorm=None,
    # clipvalue=None,
    # global_clipnorm=None,
    # use_ema=False,
    # ema_momentum=0.99,
    # ema_overwrite_frequency=100,
    # jit_compile=True,
    name='RMSprop',
)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Loss Fn
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""                               
lossfn = tf.keras.losses.SparseCategoricalCrossentropy(
    from_logits=False,
    reduction=tf.keras.losses.Reduction.AUTO,
    name='sparse_categorical_crossentropy'
)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Summary
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
# model.compile(optimizer=optimizer, loss=lossfn, metrics=['accuracy'])
model.compile(optimizer=optimizer,
    loss=lossfn,
    metrics=['accuracy'])
    
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: FileWriter
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
if exists(checkpoint_path) :
    model.load_weights(checkpoint_path)
    print("model load: " + checkpoint_path)
    input("Press Any Key!")

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Training
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
history = model.fit( train_images, train_labels, batch_size=100, epochs=10000, callbacks=[custom_callback] )
model.save_weights(checkpoint_path)

输出：比较100个类不是问题，更新新的或没有相同的输入应选择收藏夹类。

2022-11-26 12:02:17.507553: I tensorflow/stream_executor/cuda/cuda_dnn.cc:368] Loaded cuDNN version 8100
500/500 [==============================] - 34s 54ms/step - loss: 10.1518 - accuracy: 0.0104
Epoch 2/10000
500/500 [==============================] - 27s 53ms/step - loss: 9.5093 - accuracy: 0.0122
Epoch 3/10000
500/500 [==============================] - 26s 53ms/step - loss: 9.2861 - accuracy: 0.0127
Epoch 4/10000
462/500 [==========================>...] - ETA: 2s - loss: 9.1570 - accuracy: 0.0126

输出：图像已分类，类型数量不是影响太多，而是它们的一致程度，等待CIFAR100训练时...