samxzhang
Results
1
comments of
samxzhang
trafficstars
cause tf1.2.1 has a different definition of tf.nn.sampled_softmax_loss try the following code____________ def sampled_loss(labels, logits): labels = tf.reshape(labels, [-1, 1]) return tf.nn.sampled_softmax_loss(tf.transpose(w), b, labels, logits, config.NUM_SAMPLES, config.DEC_VOCAB)