Viktor Tóth

@nakosung you mean feeding a spectrogram to a convnet? it doesn't work well, you lose phase information, and that happens to be important for sound discrimination. as an analogy, the...

I have part of the `laion2B-en-aesthetic` downloaded already (55M images) in webdataset format and would like to filter it (and not re-download again). Is there a way now to do...

Here's a version of `clip_filter` I just implemented, that handles webdataset files locally or on s3, as I described above. [https://gist.github.com/csiki/1925f6a16a7000a3e47cb320fbb90c52](https://gist.github.com/csiki/1925f6a16a7000a3e47cb320fbb90c52) As @rom1504 said, it's still a little slow, especially...

I'd check how many of the words in the second sentence are actually contained in the model. It could be that because some words are encoded as the 'UNK' (unknown)...

You should provide detailed information about the error you're getting, and where exactly your code fails. On Tue, Mar 28, 2017, 6:50 AM Avhirup Chakraborty wrote: > I am having...

Have you downloaded and linked the dictionary files? It seems you have, because you're not getting any errors on that. But, the word 'pink' should be in the dictionary. Your...

You're getting Keyerror : 0, because model['utable'] and the btable counterpart are dictionaries. Basically the key is the word, the value is the word vector - and there is no...

Not that I know of. Sentences are built on the fly using the stored word vectors. On Thu, Apr 6, 2017, 8:49 AM kuhanw wrote: > Dear experts, > >...

Hey @MC-E , could you send me a link to the part of your code that uses such a technique? Do you mean the style adapter? Thanks!

Still doesn't work; installed paddleocr with pip and got the same error - in `db_postprocess.py` on line `188-191`, there are some np.int.