deep-learning-from-scratch-2

deep-learning-from-scratch-2 copied to clipboard

How to make training Simple Skip-gram model code? I try to fix your code. Plz see this issue!

1

I want to realize the code that simple Skip-gram model fit training data. So I try to it, unlike CBOW training code, I encountered the error. At first, I used...

iamcodingcat

Photo 6-22

2

Why the shape of Wx is **N** * 4H ? not **D** * 4H?

JingxinLee

def eval_seq2seq(model, question, correct, id_to_char, verbos=False, is_reverse=False): 책에서도 verbose라고 써있기도 하고, verbose라고 쓰는게 맞는 것 같아서요

J-TKim

ch08/train.pyでModuleNotFoundErrorが起きます。 ``` Traceback (most recent call last): File "/Users/segavvy/Documents/deep-learning-from-scratch-2/ch08/train.py", line 12, in from ch07.peeky_seq2seq import PeekySeq2seq File "../ch07/peeky_seq2seq.py", line 5, in from seq2seq import Seq2seq, Encoder ModuleNotFoundError: No module named...

segavvy

old code have ignored the case such as below: ``` y = array([0.88, 0.22, 0.99]) t = array([[1], [0], [1]]) ``` in such case, old `cross_entropy_error` function cannot calculate correctly,...

seiichiinoue

takahiro-itazuri


chenyongliqi

common/layersのSoftmaxWithLossの動作についてですが、現状のものでは、 forward(x, t)の引数のx, tが例えば、 x = np.array([[1.0, 1.5, 2.0], [1.2, 1.5, 1.7]]) t = np.array([[0, 0, 1], [0, 1, 0]]) または、 x = np.array([[1.0, 1.5, 2.0], [1.2, 1.5, 1.7]]) t...

tetsuomiyoshi

動作確認済みです

hitoshi44