attention transformer
seq2seq
word2vec
spell correct
windows 10 open image
- run
regedit
- go to
HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Windows Photo Viewer\Capabilities\FileAssociations
- create
문자열 값
,.jpg
,.png
,.bmp
,.gif
- copy the 값 of the exsited .tif to the new string keys above
start to linux for tencent cloud
linux edit text
vim filepath
i
,foor insertEsc
:wq
,for saving changes:q!
,for ignoring changes
추워
- Nice chrome attension for github octotree https://chrome.google.com/webstore/detail/octotree/bkhaagjahfmjljalopjnoealnfndnagc?hl=en-US
1. Error - kuza55/keras-extras#7 (comment)
InvalidArgumentError: Incompatible shapes: [21504] vs. [1024,21]
[[{{node metrics_1/acc/Equal}} = Equal[T=DT_FLOAT,
_device="/job:localhost/replica:0/task:0/device:CPU:0"]
(metrics_1/acc/Reshape, metrics_1/acc/Cast)]]
I get this error only when run my code on a GPU node (Tesla k80), ONLY on cpu- I do not get the error for batch_size = 1
- I do not get the error when I do not use metrics=['accuracy'] in compile.
- I get the error only for some particular architecture
- All the problems reported above have problems with arrays of the same dimensionality [n1,n2] vs [m1,m2] but my case is [n] vs [n/r, r]
- error occurs on my local kernel on mac with tensorflow 1.12.0, keras 2.2.4
- no error on kaggle kernel with same version as above
DaviddeMBP:~ david$ source activate tensorflow
(tensorflow) DaviddeMBP:~ david$ pip install modin
-
https://nteract.io/ download desktop app
come back home.. what to say...
2019-02-02 https://www.youtube.com/watch?v=t5qgjJIBy9g
Lets Make a Question Answering chatbot using the bleeding edge in deep learning (Dynamic Memory Network). We'll go over different chatbot methodologies, then dive into how memory networks work, with accompanying code in Keras.
Code + Challenge for this video: https://github.com/llSourcell/How_to_make_a_chatbot
Nemanja's Winning Code: https://github.com/Nemzy/language-translation/blob/master/neural_machine_translation.ipynb
Vishal's Runner up code: https://github.com/erilyth