首先，你错过了两个重塑步骤。你需要添加线条

train_x = np.expand_dims(train_x, axis=1)
train_y = np.expand_dims(train_y, axis=1)

在你定义了train_x和train_y之后（在图片的第67行之后），你输入的形状就是你第一个训练样本的形状，所以把input_shape: train_x[0]改为input_shape: train_x[0].shape，同时改变最后一个密集层的神经元数量，现在你最后一个密集层的神经元数量是Dense(len(train_y[0])...，你需要把它改为Dense(30, ...)，然后你就可以做好了。
完整的代码如下所示：

random.shuffle(training)
training = np.array(training, dtype=object)

train_x = list(training[:, 0])
train_y = list(training[:, 1])
train_x = np.expand_dims(train_x, axis=1)
train_y = np.expand_dims(train_y, axis=1)

print(len(train_x))
model = Sequential()
# model.add(Dense(128, input_shape=113, activation='relu'))
model.add(Dense(128, input_shape=train_x[0].shape, activation='relu'))
# model.add(Dense(128, input_shape=(len(train_x[0])), activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(54, activation='relu'))
model.add(Dropout(0.5))
# model.add(Dense(113, activation='softmax'))
model.add(Dense(30, activation='softmax'))

sgd =  SGD(learning_rate=0.01, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])


hist = model.fit(train_x, train_y, epochs=200, batch_size=5, verbose=1)