areylng

Results 3 issues of areylng

If you are not going to open the source code, do not put this link

![20220413085316](https://user-images.githubusercontent.com/54670610/163077869-2a09a955-16e8-460b-92b1-91e84b243f29.jpg) From this picture, most models have relatively clear judgments on the tampered area in most cases. Why can the F1 scores of most models be doubled or even tripled...

在run_youtubednn.py中,`SEQ_LEN = 50`,但是在创建`user_feature_columns`这一个变量的时候,声明的历史电影长度为10,这会影响模型的正确运行么? `VarLenSparseFeat(SparseFeat('hist_movie_id', vocabulary_size=feature_max_idx['movie_id'], embedding_dim=embedding_dim, embedding_name="movie_id"), maxlen=10, combiner='mean')` 在创建item tower的时候,X维度为(BatchSize,61) (1+1+1+1+1+50+6=61),当取item的id的时候,`self.feature_index['movie_id']`为[15:21],这会导致不能正确地按照维度取值? ![image](https://github.com/bbruceyuan/DeepMatch-Torch/assets/54670610/02665281-77e0-4ec5-8e12-876746e7f0ac)

question