def get_mask_zero_embedded(var_em, var_ph): mask = tf.equal(var_ph, 0) mask2 = tf.concat( [tf.expand_dims(~mask, -1) for i in range(EMBEDDING_DIM)], -1) rst = tf.where( mask2, tf.nn.embedding_lookup(var_em, var_ph), tf.zeros([tf.shape(var_ph)[0], tf.shape(var_ph)[1], EMBEDDING_DIM])) return rst
def build_fcn_net(self, inp, use_dice=False): with self.graph.as_default(): self.saver = tf.train.Saver(max_to_keep=1) with tf.name_scope("Out"): bn1 = tf.layers.batch_normalization(inputs=inp, name='bn1') dnn1 = tf.layers.dense(bn1, 200, activation=None, name='f1') if use_dice: dnn1 = dice(dnn1, name='dice_1') else: dnn1 = prelu(dnn1, 'prelu1') dnn2 = tf.layers.dense(dnn1, 80, activation=None, name='f2') if use_dice: dnn2 = dice(dnn2, name='dice_2') else: dnn2 = prelu(dnn2, 'prelu2') dnn3 = tf.layers.dense(dnn2, 2, activation=None, name='f3') self.y_hat = tf.nn.softmax(dnn3) + 0.00000001 with tf.name_scope('Metrics'): # Cross-entropy loss and optimizer initialization coe = tf.constant([1.2, 1.2]) coe_mask = tf.equal(self.core_type_ph, 1) coe_mask2 = tf.concat( [tf.expand_dims(coe_mask, -1) for i in range(2)], -1) self.target_ph_coe = tf.where(coe_mask2, self.target_ph * coe, self.target_ph) ctr_loss = -tf.reduce_mean(tf.log(self.y_hat) * self.target_ph) self.loss = ctr_loss # tf.summary.scalar('loss', self.loss) self.optimizer = tf.train.AdamOptimizer( learning_rate=self.lr_ph).minimize(self.loss) # self.optimizer = tf.train.GradientDescentOptimizer(learning_rate=self.lr_ph).minimize(self.loss) # Accuracy metric self.accuracy = tf.reduce_mean( tf.cast(tf.equal(tf.round(self.y_hat), self.target_ph), tf.float32)) # tf.summary.scalar('accuracy', self.accuracy) self.merged = tf.summary.merge_all()