deep-learning-from-scratch-3

deep-learning-from-scratch-3 copied to clipboard

I can't implement STEP 23 with Google Colab.

2

I can't implement STEP 23 with Google Colab. Even if I input the same as the source code, the module cannot be imported. Any good guides or tutorials on this?...

GoldSurfer

I want to visualize below graph using second order differentiation by tanh function. To realize this graph, I tried to the source code that you gave us. But this code...

young-hun-jo

`RNN.h2h` should be initialized with `in_size=hidden_size`. `steps/step59.py` is currently working because it instantiates RNN with `L.RNN(hidden_size)` (i.e., `in_size=None`), but if you instantiate like `L.RNN(hidden_size, 1)`, it throws a shape mismatch...

shionhonda

When can I get the chinese version or english version ?

5

Hi, I am a reader of your books, I have read DL from scrach 1st and 2nd edition, but I can not read japan laguage. I hope read this book...

ishuowang

I am wondering if the text inside this book can be used with google translate, like on a cell phone.

ConsciousMachines

`batch_nrom` -> `batch_norm`

shionhonda

https://github.com/oreilly-japan/deep-learning-from-scratch-3/blob/976e9bf3ad556ce06e1d6c2da78db02d52b4b6a1/dezero/core.py#L198 https://github.com/oreilly-japan/deep-learning-from-scratch-3/blob/976e9bf3ad556ce06e1d6c2da78db02d52b4b6a1/dezero/core_simple.py#L139 書籍のほうでは、後者になっています。おそらく、前者が直し忘れだと思われます。 それに関連してですが、内包表記の変数名が一貫していないのは感心しません。例えば、 https://github.com/oreilly-japan/deep-learning-from-scratch-3/blob/976e9bf3ad556ce06e1d6c2da78db02d52b4b6a1/dezero/core_simple.py#L128 こういうところで、変数名を何故xにするのでしょうか。(inputにしないのは何故なのか。outputsのときだけ変数名をoutputとするのは何故なのか) 一貫性がなくて見ていて気持ち悪いです。 ついでに書籍のほう、p.249 > y = self.outputs[0]() ここ、weakrefだから"()"をつけていることを書籍のほうのソースコード上にも"#weakref"のようにコメントがついていたほうが親切だと思います。 それから、 > x, = self.inputs tailing commaは、このコードを読まされる側としては見落としやすく、バグの原因になりやすいため、括弧をつけたほうがよろしいです。 cf.https://www.python.org/dev/peps/pep-0008/#when-to-use-trailing-commas 例) > (x,) = self.inputs

yaneurao

Implementation ideas of backpropagation of concat operator

3

**This book is the best deep learning book I have ever seen. With your help, I also wrote a framework with personal characteristics.** At the end of the study of...

owenliang

Thank you for providing such a great library for studying deep learning from scratch. I was wondering about how to implement a MeanAbsoluteError with dezero. I found that there is...

hunkim98

Use buit-in type `int` instead of deprecated `np.int`

1

Reference from numpy: _AttributeError: module 'numpy' has no attribute 'int'. `np.int` was a deprecated alias for the builtin `int`. To avoid this error in existing code, use `int` by itself....

yhirose