1
1
# Sequential model in Keras -> ASCII
2
2
3
- by [ Piotr Migdał] ( http://p.migdal.pl/ ) from [ deepsense.io ] ( http://deepsense.io/ )
3
+ by [ Piotr Migdał] ( http://p.migdal.pl/ )
4
4
5
- See: https://github.com/fchollet/keras/issues/3873
5
+ A library for [ Keras ] ( https://keras.io/ ) for investigating architectures and parameters of sequential models.
6
6
7
- ## Install
7
+ Both ` model.summary() ` and graph export were not enough - I wanted array dimensions, numbers of parameters and activation functions in one place.
8
+ I use it for didactic purpose.
9
+
10
+ * TODO
11
+ * Add ASCII art for more layers.
12
+ * Go beyond simple sequential models (e.g. to allow * merge* layers); any ideas how?
13
+ * Consider PRing to the main Keras repo, see [ #3873 ] ( https://github.com/fchollet/keras/issues/3873 ) .
14
+
15
+ ## Installation
8
16
9
17
```
10
18
pip install git+git://github.com/stared/keras-sequential-ascii.git
@@ -17,11 +25,6 @@ from keras_sequential_ascii import sequential_model_to_ascii_printout
17
25
sequential_model_to_ascii_printout(model)
18
26
```
19
27
20
- ## Rationale
21
-
22
- Both ` model.summary() ` and graph export were not enough - I wanted dimensions, numbers of parameters and activation functions in one place.
23
- I use it for didactic purpose.
24
-
25
28
## Examples
26
29
27
30
### Proof of principle
0 commit comments