frame_level_models.py 文件源码

def cnn(self,
            model_input,
            l2_penalty=1e-8,
            num_filters=[1024,1024,1024],
            filter_sizes=[1,2,3],
            sub_scope="",
            **unused_params):
        max_frames = model_input.get_shape().as_list()[1]
        num_features = model_input.get_shape().as_list()[2]

        shift_inputs = []
        for i in range(max(filter_sizes)):
            if i == 0:
                shift_inputs.append(model_input)
            else:
                shift_inputs.append(tf.pad(model_input, paddings=[[0,0],[i,0],[0,0]])[:,:max_frames,:])

        cnn_outputs = []
        for nf, fs in zip(num_filters, filter_sizes):
            sub_input = tf.concat(shift_inputs[:fs], axis=2)
            sub_filter = tf.get_variable(sub_scope+"cnn-filter-len%d"%fs,
                                         shape=[num_features*fs, nf], dtype=tf.float32,
                                         initializer=tf.truncated_normal_initializer(mean=0.0, stddev=0.1),
                                         regularizer=tf.contrib.layers.l2_regularizer(l2_penalty))
            cnn_outputs.append(tf.einsum("ijk,kl->ijl", sub_input, sub_filter))

        cnn_output = tf.concat(cnn_outputs, axis=2)
        cnn_output = slim.batch_norm(
            cnn_output,
            center=True,
            scale=True,
            is_training=FLAGS.train,
            scope=sub_scope+"cluster_bn")
        return cnn_output, max_frames