<p>tensorflow - ๊ฐ€์žฅ ๊ฐ€๊นŒ์šด KeyError</p>

์— ๋งŒ๋“  2016๋…„ 06์›” 10์ผ  ยท  3์ฝ”๋ฉ˜ํŠธ  ยท  ์ถœ์ฒ˜: tensorflow/tensorflow

์ž‘์€ ๋ง๋ญ‰์น˜์—์„œ ์ด ์ฝ”๋“œ๋ฅผ ์‹คํ–‰ํ•  ๋•Œ ํ•ด๋‹น ํ‚ค๊ฐ€ ์‚ฌ์ „์— ์—†๊ณ  ๋ง๋ญ‰์น˜ ์–ดํœ˜๋„ ๊ทธ๋ ‡๊ฒŒ ํฌ์ง€ ์•Š๊ธฐ ๋•Œ๋ฌธ์— ํ‚ค ์˜ค๋ฅ˜๊ฐ€ ๋ฐœ์ƒํ•ฉ๋‹ˆ๋‹ค.

sim = similarity.eval()
for i in xrange(valid_size):
                valid_word = reverse_dictionary[valid_examples[i]]
                print("--",valid_word)
                top_k = 5 # number of nearest neighbors

                nearest = (-sim[i, :]).argsort()[1:top_k+1]
                print(nearest)
                log_str = "Nearest to %s:" % valid_word
                print(log_str)
                for k in xrange(top_k):

                  close_word = reverse_dictionary[nearest[k]]

๋‚ด ์ถœ๋ ฅ์€ ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค.

Average loss at step  0 :  139.830688477
[[ 0.01613899 -0.06088334 -0.043384   ...,  0.02021606 -0.10094199
   0.16063547]
 [ 1.00000012  0.10277888 -0.20193034 ..., -0.04780241  0.07802841
   0.13258868]
 [ 0.09824251 -0.17075592  0.10143445 ...,  0.09903113 -0.08740355
  -0.00371696]
 ..., 
 [-0.01591019  0.02056946  0.09188825 ..., -0.0506176   0.07684846
   0.06354721]
 [-0.06749535  0.0028128  -0.09138335 ...,  0.09473826  0.04847325
  -0.00853895]
 [ 0.01795161  0.01850585  0.04632751 ...,  0.11854959  0.11196665
  -0.00684015]]
16
[-0.01613899  0.06088334  0.043384   ..., -0.02021606  0.10094199
 -0.16063547]
<type 'numpy.ndarray'>
[ 31 113 118 ..., 650 353 233]
-- using
[113 118 555 298 150]
Nearest to using:
---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-129-cf006e08ddb8> in <module>()
     87                 for k in xrange(top_k):
     88 
---> 89                   close_word = reverse_dictionary[nearest[k]]
     90                   log_str = "%s %s," % (log_str, close_word)
     91                 print(log_str)

KeyError: 555

์–ดํœ˜ ๊ธธ์ด = 1155
๋ฐฐ์น˜ ํฌ๊ธฐ = 16
embedding_size = 128
skip_window = 5
num_skips = 4

์œ ํšจํ•œ ํฌ๊ธฐ = 16
์œ ํšจํ•œ ์ฐฝ = 100
valid_examples = np.random.choice(valid_window, valid_size, replace=False)
num_sampled = 64

์•„๋ฌด๋„ ๋„์™€ ์ฃผ์‹œ๊ฒ ์Šต๋‹ˆ๊นŒ?

awaiting response

๊ฐ€์žฅ ์œ ์šฉํ•œ ๋Œ“๊ธ€

์•ˆ๋…•ํ•˜์„ธ์š” ๋ผํ›Œ,

์˜ค๋ฅ˜๊ฐ€ ๋ฐœ์ƒํ•˜๊ธฐ ์ง์ „์— "print(len(reverse_dictionary))"๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ "reverse_dictionary" ๋ฐฐ์—ด์˜ ํฌ๊ธฐ๋ฅผ ํ™•์ธํ•  ๋•Œ๊นŒ์ง€ ๋‚˜๋Š” ๋‹น์‹ ๊ณผ ๋˜‘๊ฐ™์€ ๋ฌธ์ œ๋ฅผ ๊ฒช๊ณ  ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.

"vocabulary_size = 50000" ์ค„์„ ๋” ๋‚ฎ๊ฒŒ ์„ค์ •ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. "reverse_dictionary"์˜ ๊ธธ์ด๋ฅผ ์ธ์‡„ํ•˜์—ฌ ๋ฐ˜ํ™˜๋œ ๊ฐ’์œผ๋กœ ์„ค์ •ํ–ˆ๋Š”๋ฐ ๋” ์ด์ƒ ๋ฌธ์ œ๊ฐ€ ์—†์—ˆ์Šต๋‹ˆ๋‹ค.

์ด๊ฒŒ ๋„์›€์ด ๋˜๊ธธ ๋ฐ”๋ž€๋‹ค.

๋ชจ๋“  3 ๋Œ“๊ธ€

์•ˆ๋…•ํ•˜์„ธ์š” ๋ผํ›Œ,

์˜ค๋ฅ˜๊ฐ€ ๋ฐœ์ƒํ•˜๊ธฐ ์ง์ „์— "print(len(reverse_dictionary))"๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ "reverse_dictionary" ๋ฐฐ์—ด์˜ ํฌ๊ธฐ๋ฅผ ํ™•์ธํ•  ๋•Œ๊นŒ์ง€ ๋‚˜๋Š” ๋‹น์‹ ๊ณผ ๋˜‘๊ฐ™์€ ๋ฌธ์ œ๋ฅผ ๊ฒช๊ณ  ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.

"vocabulary_size = 50000" ์ค„์„ ๋” ๋‚ฎ๊ฒŒ ์„ค์ •ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. "reverse_dictionary"์˜ ๊ธธ์ด๋ฅผ ์ธ์‡„ํ•˜์—ฌ ๋ฐ˜ํ™˜๋œ ๊ฐ’์œผ๋กœ ์„ค์ •ํ–ˆ๋Š”๋ฐ ๋” ์ด์ƒ ๋ฌธ์ œ๊ฐ€ ์—†์—ˆ์Šต๋‹ˆ๋‹ค.

์ด๊ฒŒ ๋„์›€์ด ๋˜๊ธธ ๋ฐ”๋ž€๋‹ค.

๋งŽ์€ ๋„์›€์ด ๋˜์—ˆ์Šต๋‹ˆ๋‹ค!!!!! @tcheightyeight

์ตœ๊ทผ ํ™œ๋™์ด ์—†์–ด์„œ ์ž๋™์œผ๋กœ ๋‹ซํž™๋‹ˆ๋‹ค. ์ถ”๊ฐ€ ์ •๋ณด๊ฐ€ ๋‚˜์˜ค๋ฉด ๋‹ค์‹œ ์—ด์–ด์ฃผ์„ธ์š”.

์ด ํŽ˜์ด์ง€๊ฐ€ ๋„์›€์ด ๋˜์—ˆ๋‚˜์š”?
0 / 5 - 0 ๋“ฑ๊ธ‰