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 = num_extend
        lstm_size = FLAGS.lstm_cells
        pool_size=2
        cnn_input = model_input
        num_filters=[256,256,512]
        filter_sizes=[1,2,3]
        features_size = sum(num_filters)
        final_probilities = []
        moe_inputs = []
        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))
            cnn_output = tf.nn.relu(cnn_output)
            cnn_multiscale = self.rnn(cnn_output,lstm_size, num_frames,sub_scope="rnn%d"%(layer+1))
            moe_inputs.append(cnn_multiscale)
            final_probility = self.sub_moe(cnn_multiscale,vocab_size,scopename="moe%d"%(layer+1))
            final_probilities.append(final_probility)
            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)
            num_frames = tf.maximum(num_frames//pool_size,1)

        final_probilities = tf.stack(final_probilities,axis=1)
        moe_inputs = tf.stack(moe_inputs,axis=1)
        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", moe_inputs, weight2d), dim=1)
        result = {}
        result["prediction_frames"] = tf.reshape(final_probilities,[-1,vocab_size])
        result["predictions"] = tf.reduce_sum(final_probilities*weight,axis=1)
        return result