-
Hi @lzfelix, I am using the CRF layer for a sequence tagging problem in an Active Learning framework. To compute some useful measures for this Active Learning framework, it would be very useful to get…
-
It would be nice to add a configuration page where some diagnostic data (Word/sec, etc.) can be shown. It shall provide a way to edit the learned words dictionary. The page should serve as a bug repor…
-
I finally have a little bit of time to write down what I have been doing on this front, so I wanted to open an issue here to keep track of the progress I have made, just in case anyone wants to give m…
-
Hello, thank you for your work!
I have few questions about your work.
1. The BLIP-2 model is used to create captions of images to be used as prompts for the LMTraj-SUP model. As far as I understan…
-
@jscuds @vsavram I didn't make this clear in #1, but there are 2 places in the LUNA algo where it will be useful to experiment with numerical methods: 1) The overall optimization algo, the focus of #…
-
The difference at training time, where the model is always using the correct input for predicting the next token, and the inference time, where the model is dependent only on generated tokens to predi…
-
Hi, after saving the model in train_RNN.py,
I loaded the model using `model_from_json("model.json")` and `model.load_weights("model.h5")`
I called the generate_smile(model,'CCCC')
I got the follo…
-
Prediction code is well utilized.
Thank you for the intuitive usage.
I am trying to learn about Reconstruction this time, but I encountered the following error.
**RuntimeError: Given groups=1…
-
I'd like to use STHN on my own data. I see that I should format it like the example data; however, I'm not sure what all the columns are in the example data:
| idx | src | dst | time | label | ext_…
-
I did a small experiment after watching your tutorial
the idea is to convert each token (a word in my case) into a sin signal.
I take a context_length word token and I sum up their signal (I add shi…