├── classifier_multi_label
    └── classifier_multi_label
    └── classifier_multi_label_textcnn
    └── classifier_multi_label_denses
    └── classifier_multi_label_seq2seq

Contributors

Stargazers

Forkers

helloasr zhaolulul richiesui superrichiesui zhongyunuestc hongliang632 xiaohei037 yanqiangmiffy ailwg sanghy djpasserby orangeices wonder2025 anigi98932 huangxiancun 1163710123 zhangshuo1996 flxuru advancer-debug shadowkiller33 cui-83 bestjex forestlee ares3366 michaeldengxyz ethanlovequeen silvaq jiecai08 fujianwei allen-lzh libingqi-svg zhangzhiqiangccm tangdafu gracebaoxp little-bigtiger seatonsun ericdoug-qi dystudio aka-zyq vrteye jim2016713 karen4tree xu-liang-liang 1abner1 efwfe pwwq0909 coco11563 lxz1992 feihuamantian kmftcy mondon11 dumpmemory greenary-john kandyjam chrliedong s-gege xmxoxo zengqingxue owilla wzhwzhwzhwzh tonyjxc vegech1cken fanjh990 elben7ws raogj cleverxiaohong vincentxkw wang-s-y wangscdm yingyingfan0059 li-du keanubai fingerscross diuzi jackyin68 yushuhan1 masterdxy flickerliu sjyttkl fat-ki goaller miningmouse mikite colinshin shimu007 flyrainkey ajunlonglive zhaoxuangithub wingjson wjx-shendu bangguowei kecenguo hongdangshao smallball8 xiaoguo1992 yadanxin jadenfk zl-yf escribir3 techthiyanes

def textcnn(x):
    pooled_outputs = []

    filter_sizes = [2, 3, 4, 5, 6, 7]
    inputs_expand = tf.expand_dims(x, -1)
    for filter_size in filter_sizes:
        filter_shape = [filter_size, 312, 1, 128]
        W = tf.Variable(tf.random.truncated_normal(filter_shape, stddev=0.1), dtype=tf.float32, name="W")
        b = tf.Variable(tf.constant(0.1, shape=[128]), dtype=tf.float32, name="b")
        conv = tf.nn.conv2d(
            inputs_expand,
            W,
            strides=[1, 1, 1, 1],
            padding="VALID",
            name="conv")
        # Apply nonlinearity
        h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
        # Maxpooling over the outputs
        pooled = tf.nn.max_pool(
            h,
            ksize=[1, 60 - filter_size + 1, 1, 1],
            strides=[1, 1, 1, 1],
            padding='VALID',
            name="pool")
        pooled_outputs.append(pooled)
    # Combine all the pooled features
    num_filters_total = 128 * len(filter_sizes)
    h_pool = tf.concat(pooled_outputs, 3)
    h_pool_flat = tf.reshape(h_pool, [-1, num_filters_total])

    return h_pool_flat

def get_label(sentence):
    """
    Prediction of the sentence's label.
    """
    feature = get_feature_test(sentence)
    fd = {MODEL.albert.input_ids: [feature[0]],
          MODEL.albert.input_masks: [feature[1]],
          MODEL.albert.segment_ids:[feature[2]],
          }
    prediction = MODEL.sess.run(MODEL.albert.predictions, feed_dict=fd)[0]
    print(prediction)
    r=[]
    for i in range(len(prediction)):
        if prediction[i]!=0.0:
            r.append(id2label(i))
    return r
    #return [id2label(l) for l in np.where(prediction==1)[0] if l!=0]