[英]Problem with input and output shapes in Flatten() layer in Tensorflow
[英]Incompatible shapes in output layer - Tensorflow
我正在尝试在 tensorflow 环境 google colab 中构建双 LSTM 模型。 在训练过程中,模型有一个问题:最后一层说存在形状不兼容。 我想知道是否有任何方法可以重塑 x_train 和 y_train,以解决此问题
ValueError: Shapes (16, 11) and (16, 10) are incompatible
如果我将神经元单元的值更改为我的输出层,从 11 到 10,它不会给出任何错误并且可以训练模型。 但是,我希望输出为 10 而不是 11。
# current output layer (run perfectly)
tf.keras.layers.Dense (11, activation = 'softmax')
# expected output layer (shape incompatibility)
tf.keras.layers.Dense (10, activation = 'softmax')
def build_model(vocab_size, embedding_dim=64, input_length=30):
print('\nbuilding the model...\n')
model = tf.keras.Sequential([
tf.keras.layers.Embedding(input_dim=(vocab_size + 1), output_dim=embedding_dim, input_length=input_length),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(rnn_units,return_sequences=True, dropout=0.2)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(rnn_units,return_sequences=True, dropout=0.2)),
tf.keras.layers.GlobalMaxPool1D(),
tf.keras.layers.Dropout(0.1),
tf.keras.layers.Dense(64, activation='tanh'),
# softmax output layer
tf.keras.layers.Dense(10, activation='softmax')
])
# optimizer & loss
opt = 'RMSprop' #tf.optimizers.Adam(learning_rate=1e-4)
loss = 'categorical_crossentropy'
# Metrics
metrics = ['accuracy', 'AUC','Precision', 'Recall']
# compile model
model.compile(optimizer=opt,
loss=loss,
metrics=metrics)
model.summary()
return model
BATCH_SIZE 设置为 16。 y_train 和 x_train 的形状为:
x_train.shape
(800, 30)
y_train.shape
(800,)
def train(model, x_train, y_train, x_validation, y_validation,
epochs, batch_size=32, patience=5,
verbose=2, monitor_es='accuracy', mode_es='auto', restore=True,
monitor_mc='val_accuracy', mode_mc='max'):
print('\ntraining...\n')
# callback
early_stopping = tf.keras.callbacks.EarlyStopping(monitor=monitor_es,
verbose=1, mode=mode_es, restore_best_weights=restore,
min_delta=1e-3, patience=patience)
model_checkpoint = tf.keras.callbacks.ModelCheckpoint('tfjsmode.h5', monitor=monitor_mc, mode=mode_mc,
verbose=1, save_best_only=True)
# Define Tensorboard as a Keras callback
tensorboard = TensorBoard(
log_dir='./logs',
histogram_freq=1,
write_images=True
)
keras_callbacks = [tensorboard, early_stopping, model_checkpoint]
# train model
history = model.fit(x_train, y_train,
batch_size=batch_size, epochs=epochs, verbose=verbose,
validation_data=(x_validation, y_validation),
callbacks=keras_callbacks)
return history
def preprocess(x, padding_shape=30):
return np.array([ord(i.lower()) - ord('a')+1 if not i.isdigit() and i != ' ' else 0 for i in list(x)] + ([0] * (padding_shape - len(x))), dtype=int)
def prepare_dataset(labeldict : dict, test_size=.3, validation_size=.1):
print('preparing the dataset...\n')
from sklearn import preprocessing
# load dataset
# split dataset (as string into panda.core.series.Serie object)
x, y = load_clean_dataset()
x = np.array(list(map(preprocess, x)))
y = np.array(list(map(lambda x: labeldict[x.replace(' ', '_')], y)))
print(('y: {}').format(y))
# create/split train, validation and test and shuffle the data
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=test_size, shuffle=True)
print(x.max(), x.min())
x_train_val, x_validation, y_train_val, y_validation = train_test_split(x_train, y_train, test_size=test_size, shuffle=True)
# pandas.core.series.Series to numpy array
x_train, y_train = np.array(x_train), np.array(y_train)
x_validation, y_validation = np.array(x_validation), np.array(y_validation)
x_test, y_test = np.array(x_test), np.array(y_test)
x_train_val, y_train_val = np.array(x_train_val), np.array(y_train_val)
print(('\nx_train: \n{}\n\ny_train: \n{}').format(x_train_val, y_train_val))
y_train = tf.keras.utils.to_categorical(y, num_classes=10)
return (x_train, y_train), (x_validation, y_validation), (x_test, y_test), (x_train_val, y_train_val)
看来您目前将标签作为整数(即不是单热编码向量)。 例如你的y
似乎是这样的,
[0, 1, 8, 9, ....] # a vector of 800 elements
有两种方法可以在此类数据上训练模型。
使用sparse_categorical_crossentropy
作为模型的损失函数
model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=metrics)
使用以下方法将您的标签转换为单热编码,
y_onehot = tf.keras.utils.to_categorical(y, num_classes=10)
然后将模型的损失保持为categorical_crossentropy
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.