You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
# Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
38
+
39
+
steps:
40
+
- name: Checkout repository
41
+
uses: actions/checkout@v3
42
+
43
+
# Initializes the CodeQL tools for scanning.
44
+
- name: Initialize CodeQL
45
+
uses: github/codeql-action/init@v2
46
+
with:
47
+
languages: ${{ matrix.language }}
48
+
# If you wish to specify custom queries, you can do so here or in a config file.
49
+
# By default, queries listed here will override any specified in a config file.
50
+
# Prefix the list here with "+" to use these queries and those in the config file.
51
+
52
+
# Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
53
+
# queries: security-extended,security-and-quality
54
+
55
+
56
+
# Autobuild attempts to build any compiled languages (C/C++, C#, Go, or Java).
57
+
# If this step fails, then you should remove it and run the build manually (see below)
58
+
- name: Autobuild
59
+
uses: github/codeql-action/autobuild@v2
60
+
61
+
# ℹ️ Command-line programs to run using the OS shell.
62
+
# 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
63
+
64
+
# If the Autobuild fails above, remove it and uncomment the following three lines.
65
+
# modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
[Complex-valued convolutions](https://en.wikipedia.org/wiki/Convolution#Domain_of_definition) could provide some interesting results in signal processing-based deep learning. A simple(-ish) idea is including explicit phase information of time series in neural networks. This code enables complex-valued convolution in convolutional neural networks in [keras](https://keras.io) with the [TensorFlow](https://tensorflow.org/) backend. This makes the network modular and interoperable with standard keras layers and operations.
11
5
@@ -17,20 +11,15 @@ Requirements
17
11
- numpy
18
12
- scipy
19
13
- scikit-learn
20
-
- keras
21
-
- tensorflow 1.X or tensorflow-gpu 1.X
14
+
- tensorflow 2.X
22
15
23
16
Install requirements for computer vision experiments with pip:
24
-
```
25
-
pip install -f requirements.txt
26
-
```
27
17
28
-
For the non-gpu version:
29
18
```
30
-
pip install -f requirements-nogpu.txt
19
+
pip install -r requirements.txt
31
20
```
32
21
33
-
Depending on your Python installation you might want to use anaconda or other tools.
22
+
Depending on your Python installation you might want to use anaconda or venv or other tools.
34
23
35
24
36
25
Installation
@@ -39,16 +28,12 @@ Installation
39
28
```
40
29
pip install keras-complex
41
30
```
42
-
and
43
-
```
44
-
pip install tensorflow-gpu
45
-
```
46
31
47
32
Usage
48
33
-----
49
34
Build your neural networks with the help of keras.
An example working implementation of an autoencoder can be found [here](https://github.com/JesperDramsch/Complex-CNN-Seismic/).
70
55
71
-
Citation
72
-
--------
56
+
Complex Format of Tensors
57
+
-------------------------
73
58
74
-
Please cite the original work as:
59
+
This library assumes that complex values are split into two real-valued parts. The real-valued and complex-valued complement, also seen [in the Docs](https://keras-complex.readthedocs.io/math.html).
60
+
61
+
The tensors for a 2D complex tensor of 3x3, the look like:
75
62
76
63
```
77
-
@ARTICLE {Trabelsi2017,
78
-
author = "Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, João Felipe Santos, Soroush Mehri, Negar Rostamzadeh, Yoshua Bengio, Christopher J Pal",
79
-
title = "Deep Complex Networks",
80
-
journal = "arXiv preprint arXiv:1705.09792",
81
-
year = "2017"
82
-
}
64
+
[[[r r r],
65
+
[r r r],
66
+
[r r r]],
67
+
[i,i,i],
68
+
[i,i,i],
69
+
[i,i,i]]]
83
70
```
84
71
85
-
Cite this software version as:
72
+
So multiple samples should then be arranged into `[r,r,r,i,i,i]`, which is also documented [in the Docs](https://keras-complex.readthedocs.io/math.html#implementation).
73
+
74
+
Citation
75
+
--------
76
+
77
+
Find the [CITATION file](/CITATION.cff) or cite this software version as:
86
78
```
87
79
@misc{dramsch2019complex,
88
80
title = {Complex-Valued Neural Networks in Keras with Tensorflow},
@@ -93,3 +85,14 @@ Cite this software version as:
93
85
year = {2019}
94
86
}
95
87
```
88
+
89
+
Please cite the original work as:
90
+
91
+
```
92
+
@ARTICLE {Trabelsi2017,
93
+
author = "Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, João Felipe Santos, Soroush Mehri, Negar Rostamzadeh, Yoshua Bengio, Christopher J Pal",
0 commit comments