-
Right now the code path is to download some pretrained embedding from a remote source. However I have some domain specific embeddings that are in the standard gensim format. Would it be possible to su…
-
I use Class org.deeplearning4j.spark.models.embeddings.word2vec.Word2Vec to do word-embedding with multiple GPUs. And have a problem, tasks on stage 4 can never get finished. I paste some code and log…
-
Hi! Thanks for sharing the code
When I try to run the code `python train_GPU.py`
I met
> Traceback (most recent call last):
> File "train_GRU.py", line 243, in
> tf.app.run()
> File…
-
[Excuse me,my python version is 3.5 and tensorflow version is 1.2.1，But I had some trouble when debug it.Here is the error I encountered:
C:\Users\Administrator\AppData\Local\Programs\Python\Python…
-
根据github上 https://github.com/PaddlePaddle/Paddle/tree/develop/doc/howto/usage/cluster/src/word2vec 跑GPU分布式WordEmbedding模型，环境变量如下：
```
export PADDLE_INIT_USE_GPU=True
export PADDLE_INIT_PORT=7164
e…
-
Changing the cell type to LSTM throws an error (with default parameters and code):
`ValueError: Shape must be rank 2 but is rank 3 for 'model/concat' (op: 'ConcatV2') with input shapes: [?,30], [?,…
-
Big problem. Almost %25 of words are unknown:
```
number_of_unknown_tokens: 1211
len(token_count['train']): 4593
```
with Lionel's embedding:
```
number_of_unknown_tokens: 1593
len(token_count…
-
Loading `GoogleNews-vectors-negative300.bin` from original word2vec website fails. Loaded word embedding have shape of `(0, 4687957)`.
```python
from word_embedding_loader import WordEmbedding
…
-
I trained a model using the latest CNTK on windows, and save the model after training.
Now I want to output the value of a node called `embedding` in the model which is defined as:
`embedding = Para…
-
For example,
How to concatenate image embedding and word embeddings together as one sequence which is then fed to LSTM just like what is done in Google's image caption generation paper http://arxiv.or…