-
Thanks for the great paper!
I've created another open source implementation of the SHA RNN here: https://github.com/talonvoice/sha-rnn
I trained with similar parameters to the single head model …
-
Hi,
I wanted to use the sentiment transfer script + load my pretrained lm model. But this fails:
```bash
python3 sentiment_transfer.py -experiment_dir ./experiments -experiment_name mlstm -mode…
-
In the original paper, it is said that each program is divided into many short segments (len=50) to feed into model respectively and **they are interacted by reusing the hidden states and memory state…
-
In Model section, you show two neural network framework,e.g Glove embeddings with 1D-CNN and FastText embedding with single layer LSTM. It's hard for me to figure out these NNs.
Can you share some t…
-
I have a simple question. I tried to solve it but didn't make it. I want to update the higher layers of bert while keep the lower layers fixed. For example, the below INFO. If I want to keep the layer…
-
https://gitee.com/paddlepaddle/models/tree/develop/PaddleCV/video/application/video_tag运行test失败啊啊啊啊
`%cd ~/video_tag/
!python videotag_test.py
/home/aistudio/video_tag
/opt/conda/envs/pyth…
-
error brought to my attention by S. Mamont for formula 29, linear correlation:
-
My email is 775301251@qq.com
-
I just downloaded OpenNMT & attempted to train using the demo data set and ended up with an illegal memory access error.
Command that I ran -
`CUDA_LAUNCH_BLOCKING=1 th train.lua -data data/demo-tr…
-
When I run AT-LSTM.py python file I am getting an error like below. Every step train cost value is becoming Nan
the 100 step, train cost is: nan
the 200 step, train cost is: nan
the 300 step, tra…