Chang-Uk Shin
Chang-Uk Shin
No. Please see step 6.2 in train.py The variable ‘path’ is the path of best model. Not the latest model. We assume the least validation loss model is the best...
The `predictions` operation is passed to process to the tensorflow session at line 63 of predict.py. If you want to get the probability distribution of the classes, you can pass...
It was maybe due to the lack of learning iteration or lack of data size.
Just in my opinion, repeating same words means 'not yet fitted'. And it said 'loss: nan'. It means something is not good.(very high loss or ...) please re-consider to set...
I have same situation with @felicialiu My backtrace is Program received signal SIGSEGV, Segmentation fault. [Switching to Thread 0x7fffd7578700 (LWP 10260)] 0x0000000000409418 in TrainModelThread () at word2vec.c:928 928 for (c...
@wlin12 btw, when I disable 'hs', It's good to go. Hope it helps.
Yes. you are right. `svg g.arcs text { fill #e0a; }` I didn't catch you. I don't use any xml files for this.. I think.