indiejoseph / doc-han-att Goto Github PK

如何确定这两个参数呢？另外如何理解这两个参数，看了论文还是不懂，谢谢了

PoolAllocator: After 46502 get requests, put_count=46422 evicted_count=1000 eviction_rate=0.0215415 and unsatisfied allocation rate=0.0253753
2017-10-19 20:46:08.469526: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 100 to 110

Traceback (most recent call last):
File "train.py", line 7, in
from model import Model
File "/software/home/zhongsl/han005/model.py", line 6, in
from ran_cell import RANCell
File "/software/home/zhongsl/han005/ran_cell.py", line 10, in
from tensorflow.contrib.rnn.python.ops import core_rnn_cell_impl
ImportError: cannot import name 'core_rnn_cell_impl'
谢谢！Thanks！

hello ！there is no embed.npy in dir data.

I encountered the following issue when running your code:
InvalidArgumentError (see above for traceback): indices[0,6,12] = 2239 is not in [0, 2192)
[[Node: model_1/embedding_lookup = Gather[Tindices=DT_INT64, Tparams=DT_FLOAT, _class=["loc:@model/embedding"], validate_indices=true, _device="/job:localhost/replica:0/task:0/cpu:0"](model/embedding/read, _recv_model_1/inputs_0)]]

Accrding to the last lssue, i guess my the cropus I used was too small so the embedding_lookup is out of index. Can you please share your training cropus or embed if it is possible since I have difficult in obtaining the cropus?
Thank you.

As I observed, there will be an out-of-vocabulary error throwing out when using the "embedding_lookup"
Error looks like:

InvalidArgumentError (see above for traceback): indices[0,1,3] = 6501 is not in [0, 6342)
[[Node: model_1/embedding_lookup = Gather[Tindices=DT_INT64, Tparams=DT_FLOAT, class=["loc:@model/embedding"], validate
indices=true, _device="/job:localhost/replica:0/task:0/cpu:0"](model/embedding/read, _recv_model_1/inputs_0)]]

See geek-ai/irgan#9

Nothing wrong with your code, it sounds like a known issue in Tensorflow (CPU version)