我正在编写一个程序,根据它经过训练的名称(字符级编码)来预测随机名称。我的输出形状为(44,27),我的密集层设置为提供27类softmax输出。我仍然收到ValueError。
我尝试将轴添加到输出中
(Y_train_oh = np.expand_dims(Y_train_oh, axis=2))
。
def model1(vocab_len):
model = Sequential()
model.add(LSTM(128,input_shape=(buff_length, vocab_len)))
model.add(Dense(units=60, activation='relu'))
model.add(Dense(units=vocab_len, activation='softmax'))
model.summary()
return model
def one_hot(Y, char2idx, vocablen):
Ty = len(Y)
Yoh = np.zeros((Ty, vocablen))
for idx in range(Ty):
Yoh[idx, char2idx[Y[idx]]] = 1
return Yoh
def trainer(X, vocab, char2idx, no_epochs=1, batch_size=10):
model = model1(len(vocab))
model.compile(optimizer='Adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
for epn in range(no_epochs):
np.random.seed(1 + epn)
Tx = len(X)
indices = np.random.randint(0, Tx, batch_size)
X_train = []
Y_train = []
for index in indices:
name = str(X[index])
for chIndex in range(len(name) - 1):
if chIndex >= buff_length - 1:
X_train.append(name[chIndex - buff_length + 1: chIndex + 1])
Y_train.append(name[chIndex + 1])
for i in range(len(X_train)):
print ((X_train[i] + ' : '+ Y_train[i]) )
X_train_oh = np.copy(one_hot_buffer(X_train, char2idx, len(vocab)))
Y_train_oh = np.copy(one_hot(Y_train, char2idx, len(vocab)))
print(X_train_oh.shape,':',Y_train_oh.shape)
model.fit(x=X_train_oh, y=Y_train_oh)
model.save('name_model.h5')
错误消息:
ValueError:检查目标时出错:预期density_10具有 形状(1,),但数组的形状为(27,)