frame_level_models.py 文件源码

def create_model(self, model_input, vocab_size, num_frames, l2_penalty=1e-8, **unused_params):

        num_extend = FLAGS.moe_num_extend
        num_layers = 10
        pool_size=2
        cnn_input = model_input
        num_filters=[256,256,512]
        filter_sizes=[1,2,3]
        features_size = sum(num_filters)

        for layer in range(num_layers):
            cnn_output, num_t = self.cnn(cnn_input, num_filters=num_filters, filter_sizes=filter_sizes, sub_scope="cnn%d"%(layer+1))
            if layer < 3:
                num_t = pool_size*(num_t//pool_size)
                cnn_output = tf.reshape(cnn_output[:,:num_t,:],[-1,num_t//pool_size,pool_size,features_size])
                cnn_input = tf.reduce_max(cnn_output, axis=2)
            else:
                cnn_input = cnn_output

        cnn_output, num_t = self.kmax(cnn_input, num_filters=features_size, filter_sizes=num_extend, sub_scope="kmax")
        cnn_input = tf.reshape(cnn_output,[-1,features_size])
        final_probilities = self.sub_moe(cnn_input,vocab_size)
        final_probilities = tf.reshape(final_probilities,[-1,num_extend,vocab_size])
        weight2d = tf.get_variable("ensemble_weight2d",
                                   shape=[num_extend, features_size, vocab_size],
                                   regularizer=slim.l2_regularizer(1.0e-8))
        weight = tf.nn.softmax(tf.einsum("aij,ijk->aik", cnn_output, weight2d), dim=1)
        result = {}
        result["predictions"] = tf.reduce_sum(final_probilities*weight,axis=1)
        return result