Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 3 years ago.
Improve this question
I am currently training the standard DCGAN network on my dataset. After 40 epochs, the loss of both generator and discriminator is 45-50. Can someone please explain the reason and possible solution for this?
This interpretation may be added to unsolved problems.
You cannot interpret the loss of generator and discriminator. Since when one improves it will be harder for the other. When generator improves it will be harder for the critic. When critic improves it will be harder for the generator.
The values totally depend on your loss function. You may expect that numbers should be "about the same" over time.
Related
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 3 years ago.
Improve this question
I understand that Chisel is a HDL/HCL language to overcome some of Verilog/SystemVerilog restrictions by using higher abstraction level.
And it is open source as well.
It might be a bit naive and presumptuous, but still I would like to ask.
My question is that why do so many similar efforts are working in parallel, e.g. Blusspec, spinalHDL, Pyha etc?
I mean, is there any reason why the development community may not choose one of these and concentrate efforts on stabilizing or enhancing one of these.
That's exactly what is happening now, it just takes a while to choose.
Although the past does not show that the best technology wins, let us hope it does this time.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I'm very new to NLP and Deep Learning field and want to understand that after vectorization of a whole corpus using Word2Vec, Do I need to store the word vector values locally?
If yes I want to make a chatbot for android. Can anyone please guide me for this?
word2vec embeddings can be saved:
in first layers of your deep model. It's rare approach, because in this case you can't use this word2vec for other tasks.
as independent file on disk. It's more viable apporach for most use cases.
I'd suggest to use gensim framework for training of word2vec. Here you can learn more how to train word2vec and save them to disk: https://radimrehurek.com/gensim/models/word2vec.html
Particularly, saving is performed via:
model = Word2Vec(common_texts, size=100, window=5, min_count=1, workers=4)
model.save("word2vec.model")
Training of chatbot is much more difficult problem. I can try to suggest you a possible workflow, but you should to clarify what type of chatbot do you have in mind? E.g. should it answer on any question (open domain)? Should it generate answers or it will have predefined answers only?
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
Do any languages that support retry constructs in exception handling track and expose the number of times their catch/rescue (and/or try/begin) blocks have been executed in a particular run?
I find myself counting (and limiting) the number of times a code block is re-executed after an exception often enough that this would be a handy language built-in.
This is a really interesting question. I did a little research and apparently there is a design pattern called the circuit breaker pattern which was developed to handle such things. I have never heard of the pattern before and can't find much information about it.
There is a library which handles retrying an event for .NET available, might be worth a look. Heres a link to an article about it:
http://www.tobinharris.com/past/2009/1/26/net-circuit-breakers/
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 4 years ago.
Improve this question
I had to do a overview for a customer meeting, and they requested flow charts. It had never occurred to me that there was no switch symbol in any of the flow charting I've seen. I know functionally they are similar, but documentation should represent the code you've written or are planning too. Maybe I'm just being picky, but it seems like a common enough construct that it would have "representation."
Pete
My impression is that diamonds are the correct symbol for switches (multidirectional branches) as well as binary decision points — i.e. the diamond is any conditional. One just gets the idea that diamonds are for either/or because that's their most common use.
The difference between a series of if's and a switch is irrelevant at the flow chart level. Both are a series of conditionals. If you want to document your code down to the if/switch level, just print out the code.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 8 years ago.
Improve this question
Upon reading a blog post about a minimalist story-generating python program, I was asking myself - and you - which are the most successful attempts at such programs. I remember seeing something using generating grammars, for instance. And which are the best attempts that, like this one, are extremely compact, either self-contained or able to read, say, the Web or an independent textual corpus (but not simply a file with a large number of story chunks)?
Search for Talespin for some famous ground breaking work. (Example: Micro-Talespin in Common Lisp by Warren Sack.)
I actually like Turner's "Minstrel: A Computer Model of Creativity and Storytelling" better :
ftp://ftp.cs.ucla.edu/tech-report/1992-reports/920057.pdf
Talespin is, in my opinion, blind in it's algorithm to everything but planning. So the author goals are given very little consideration (if at all). Minstrel is better that way.