-
## Description
I am trying text generation example with GTP2 as shown [here](http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-1010/8/model_zoo/text_generation/index.html):
I am us…
-
Images are in wrong order/position on page:
https://gluon.mxnet.io/chapter01_crashcourse/introduction.html
But all good on corresponding Github:
https://github.com/zackchase/mxnet-the-straight-do…
-
## Description
- I want to train BERT model on GPU, but have some problems. My configuration:
* Software environment: Python: 3.7.7, Cuda: 10.2
* Install MXNet: `pip install mxnet-cu102` , ve…
-
## Description
`mxnet.gluon.nn.instancenorm` output NaN
## To Reproduce
~~~python
import mxnet
layer=mxnet.gluon.nn.InstanceNorm()
layer.initialize()
input=mxnet.nd.array([[[[ 1.4918449e+3…
DNXie updated
3 years ago
-
Input:
`X, Y = getfake(50, 2, 0.3)`
`tmp
[[ 0.41137779 1.77428079]]
`
`X[i,:]
[ 0. 0.]
`
`X
`
`Y
[ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0.…
-
Recently engaged in NLP work, has been concerned about mxnet, want to add bi-lstm CRF model, TF already has a CRF module, Hope Mxnet and gluon as soon as possible. Thank you
-
We can see the CI will pass seemingly randomly:
fail
https://ci.gluon.ai/blue/rest/organizations/jenkins/pipelines/GluonNLP-py3-gpu-integration/branches/PR-1521/runs/11/log/?start=0&download=true/…
leezu updated
3 years ago
-
## Description
When setting sparse_grad=True in mxnet.gluon.nn.Embedding() I get an error.
### Error Message
The error is:
Check failed: is_valid: Embedding input contains data out of bound
…
-
I am using the bert model from gluonnlp (`bert_12_768_12`, `book_corpus_wiki_en_uncased`).
Since, I wanted to be able to switch betweem bert and roberta, I am using the BERTSentenceTransform that is …
-
In the documentation here : https://github.com/dmlc/gluon-nlp/blob/master/docs/examples/sentence_embedding/bert.md in the "Conclusion" points to this broken link ( https://github.com/dmlc/gluon-nlp/bl…