错误 ValueError：转换后的代码：
<ipython-input-63-1e3afece3370>:10 train_step *
loss += loss_func(targ, logits)
<ipython-input-43-44b2a8f6794e>:11 loss_func *
loss_ = loss_object(real, pred)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/losses.py:124 __call__
losses = self.call(y_true, y_pred)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/losses.py:216 call
return self.fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/losses.py:973 sparse_categorical_crossentropy
y_true, y_pred, from_logits=from_logits, axis=axis)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/backend.py:4431 sparse_categorical_crossentropy
labels=target, logits=output)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/nn_ops.py:3477 sparse_softmax_cross_entropy_with_logits_v2
labels=labels, logits=logits, name=name)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/nn_ops.py:3393 sparse_softmax_cross_entropy_with_logits
logits.get_shape()))
ValueError: Shape mismatch: The shape of labels (received (128,)) should equal the shape of logits except for the last dimension (received (16, 424)).
我引用的代码使用了现时不推荐使用的legacyseq2seq.sequence_loss_by_example。所以我尝试了SparseCategoricalCrossentropy损失方法会引发相同的错误
模型（Keras）
def build_model(training=True):
input_ = tf.keras.layers.Input(shape=(unfold_max,), name='inputs')
embedding = tf.keras.layers.Embedding(input_dim=n_items + 1,
output_dim=128)(input_)
cells=[]
for _ in range(1):
cells.append(
tf.keras.layers.LSTMCell(128,
dropout=0.25,
activation=tf.keras.activations.tanh)
)
cell_output = tf.keras.layers.RNN(cells, return_state=False)(embedding)
softmax_W = tf.Variable(tf.ones(shape=(128,1 + n_items)), 'softmax_w')
softmax_b = tf.Variable(tf.zeros(shape=(n_items + 1)),'softmax_b')
output = tf.reshape(cell_output, [-1, 128])
logits = tf.matmul(output, softmax_W) + softmax_b
return tf.keras.Model(inputs=[input_], outputs=[logits])
损失功能
optimizer = tf.keras.optimizers.Adam()
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(
from_logits=True,
reduction='none')
def loss_func(real, pred):
mask = tf.math.logical_not(tf.math.equal(real, 0))
loss_ = loss_object(real, pred)
mask = tf.cast(mask, dtype=loss_.dtype)
loss_ *= mask
return tf.reduce_mean(loss_)
训练步骤
@tf.function
def train_step(inp, targ):
loss = 0
with tf.GradientTape() as tape:
logits = model(inp)
loss += loss_func(targ, logits)
variables = model.trainable_variables
gradients = tape.gradient(loss, variables)
optimizer.apply_gradients(zip(gradients, variables))
return loss
输入：[135，144，0，0，0，0，0，0]
目标：[144、127、0、0、0、0、0、0]