Dawid Smoleń

unknown instruction: <!DOCTYPE

4

After running docker I have a following error > Error response from daemon: Dockerfile parse error line 7: unknown instruction:

stack not found when running on M1

6

``` => [builder 5/7] ADD . . 0.2s => ERROR [builder 6/7] RUN stack setup 0.2s ------ > [builder 6/7] RUN stack setup: #13 0.186 /bin/sh: 1: stack: not found...

Is it possible to initialize lda2vec with some external embeddings?

3

Is it possible to initialize lda2vec with some external embeddings, f.e pre-trained FastText or pre-trained word2vec?

Questions about loss averaging in seq2seq tutorial

1

I described the issue here, but got no answer: https://discuss.pytorch.org/t/questions-about-loss-averaging-in-seq2seq-tutorial/13440

Good WER using attention-based encoder-decoder on WSJ: https://arxiv.org/abs/1811.02770?fbclid=IwAR12930xgp1Z9Fw1eJ72JkDWfGPevNZ7exP77z-Y3hkn4P1gzH5oWytGeeU

Does anyone know any real working website built on this project (with example products and users added) so that anyone can test the user experience and functionality?

MLServer custom example missing standarization during inference

1

https://github.com/SeldonIO/MLServer/blob/master/docs/examples/custom/README.md In the above example ^ I see that in the training phase the data in standardized (lambda function) and this doesn't happen in the inference, so the model would...

Do you have any models CTC

1

I'm wondering whether you used some CTC models in your research and have the implementation with compatible interfaces, even if not available on github? If yes, could you share @Canjie-Luo...

`MORN.forward()` gives different `x_rectified` depending on `debug` flag. I'm not sure if I understand it correctly but I think the only difference between debug and normal mode should be the...

After pasting the example URL that in my case is `file:///Users/dasm/projects/LabelMeAnnotationTool/tool.html?collection=0&mode=f&folder=example_folder&image=img1.jpg` I see the empty white screen in a browser. Am I missing something?