-
Why are there no files in the directionFiles/iwslt folder called valid_src_direction.txt and valid_tgt_direction.txt
-
I was training tacorton-gst for about 200 epochs on a different dataset, not LJ nor MAILABS, but a corpus on Romanian language. The model doesn't seem to converge after 200 epochs, and the inference i…
-
hi,
I am trying to replicate the Natural Language Inference (NLI) task example to train a cross-encoder on a 15 labels dataset.
When using the `distilroberta-base` I get the following error on tr…
-
Hi, thank you for sharing this code.
here are some of my thoughts about it:
as suggested in this [link](https://medium.com/ai-quest/pre-trained-language-model-in-any-language-7531ea7217d4), for tra…
-
When mkey uses a uint for time series data. The sequence of time is implied to start with zero (as epoch) and mkey values that are greater-than other mkey values are more recent. The normative languag…
-
I have modified the code for my own remote sensing data and used bounding box prompts for guidance, but during training, the IoU on the validation set is extremely poor.
我修改成自己的遥感数据,并使用框提示进行提示.但我在训练的…
-
After AMP training for this sample GluonNLP training model:
https://github.com/dmlc/gluon-nlp/compare/master...ChengXianbing:master
we found that the loss is higher than training without enabling AM…
-
good idea steal from [date – Liquid template language](https://shopify.github.io/liquid/filters/date/)
- provide helpers to format date into string
- provide helpers to return current datetime
- …
-
Type: Bug
Create a filter with the following properties:
Type: simple
Libraries: use a wildcard, e.g. o#12345* for all libraries starting o#12345
Objects: *
Object types: *SRCPF
Members: *
Me…
-
```
[12:53:11.383037] NaN loss encountered. Skipping this batch.
Traceback (most recent call last):
File "train.py", line 262, in
main(args)
File "train.py", line 230, in main
train…