tf_repos icon indicating copy to clipboard operation
tf_repos copied to clipboard

TensorFlow Script

Results 36 tf_repos issues
Sort by recently updated
recently updated
newest added

tf_repos/deep_ctr/Serving_pipeline/deep_fm_serving_client.cpp编译时碰到很多依赖问题,能否提供一下client的编译脚本,以及运行过程

是不是训练数据太不平衡了,大部分label z都是0,是否需要采样后训练?

tf_repos/deep_ctr/Feature_pipeline/get_criteo_feature.py 第50行中对离散特征编号从0, 但同时连续特征是1-13,会导致连续特征对应的embedding会和离散特征embedding相同的问题,想问下?

看到 DeepFM 中一阶项, PNN中 线性项 y_linear = tf.reduce_sum(tf.multiply(feat_wgts, feat_vals),1),输出都是一个数值而非一个向量;论文中一阶项都是一个向量而非一个数值吧?

请问在CPU集群运行分布式TF的时候遇到这个问题是咋回事?有啥解决办法吗? INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Create CheckpointSaverHook. could not find method isEncrypted from class org/apache/hadoop/fs/FileStatus with signature ()Z hdfsGetPathInfo(/user/tdw_gilbertchen/model_path/test/2019080400): getFileInfo error: java.lang.NoSuchMethodError: isEncrypted INFO:tensorflow:Graph was finalized. 2019-09-04 11:14:49.486416: I tensorflow/core/distributed_runtime/master_session.cc:1161] Start...

运行DCN模型跑下面这个数据集时候有些疑问: http://labs.criteo.com/2014/02/download-kaggle-display-advertising-challenge-dataset/ Kaggle Display Advertising Challenge Dataset 我看里面数据格式是: The columns are tab separeted with the following schema: ... ... 并没有区分用户id、商品id,那这样如何给用户做推荐呢?而且我看get_criteo_feature.py处理的时候,很多categorical 类型数据直接被截断没了,那如何区分开用户呢? parser.add_argument( "--cutoff", type=int, default=200, help="cutoff long-tailed categorical values" )...

你好,我看代码中的field_size是固定死的,但实际中如果遇到每行的field 大小不确定,因为是稀疏的, 所以就不能直接reshape了,请问有相应的解决方案吗? feat_ids = features['feat_ids'] feat_ids = tf.reshape(feat_ids,shape=[-1,field_size]) feat_vals = features['feat_vals'] feat_vals = tf.reshape(feat_vals,shape=[-1,field_size])