Arthur Wu

I had also met the same problem as you found @yathe

for (x, y) in g: ## if x in vocab and y in vocab: ix = vocab[x].index iy = vocab[y].index # N(i,r) neighbors[ix][r].append(iy) neighbors[iy][r].append(ix) add one line leading by ##...

> My modification way is in 'generate_vocab': > One more parameter ‘all_nodes’ was passed, and the following code was added. > > ``` > for i in all_nodes: > if...

> thank you very much! > I still have a question, is it impossible to get the embbeding of the nodes that have not been walked? > @wuqianliang according formula...

> thank you very much! > I still have a question, is it impossible to get the embbeding of the nodes that have not been walked? > @wuqianliang need to...

I use the SSD disk; Extracting image from ms-celeb-1m.tsv may take a long while , about several hours. I only extract 20000 persons' images for training. @xhzcyc

deepid1 , test softmax accuracy 70% deepid2 , test softmax accuracy 37% DeepID1_train_lmdb 19G DeepID1_test_lmdb 4.5G This week , I will try multipatch preprocess on train dataset. @xhzcyc

Could you share the sovler txt for deepid1 and deepid2 ? @xhzcyc my emailbox : [email protected]

Do you have a wechat ? @xhzcyc My wechat is 15715164075

> > 用的deepid2跑了四万次 准确率63是不是有点低了 > > I0305 19:09:06.048393 22020 solver.cpp:337] Iteration 40000, Testing net (#0) > > I0305 19:09:47.081173 22020 solver.cpp:404] Test net output #0: accuracy1 = 0.634328 > >...