LightCTR

LightCTR copied to clipboard

在import tensorflow后， 添加代码：tf.config.experimental_run_functions_eagerly(True)

kaohao

源代码中，很多模型的参数矩阵定义写在了call方法下面，比如autoint,fibinet

kaohao

gen_concated_feature

1

你好，我觉得gen_concated_feature.py文件中，sparse_slots_filter = [slot_name for slot_name in slots_filter if slot_name in self.sparse_feats_slots] 应该改为sparse_slots_filter = [slot_name for slot_name in slots_filter if slot_name in (self.sparse_feats_slots+self.list_sparse_feats_slots)]

chen849157649

move kernel initialization to model/layer.build()

hughian

If I code 'model.save_weights(...)' after model.fit in xDeepfm, then i get the traceback: Traceback (most recent call last): File "train_xdeepfm.py", line 74, in model.save_weights('weights/test.h5') File "/home/lixiang/anaconda3/envs/env_tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py", line 1074, in save_weights...

RisanLi