brysef / rfml Goto Github PK
View Code? Open in Web Editor NEWRadio Frequency Machine Learning with PyTorch
License: BSD 3-Clause "New" or "Revised" License
Radio Frequency Machine Learning with PyTorch
License: BSD 3-Clause "New" or "Revised" License
Hi Bryse,
I've added some for loops to your adversarial_evasion.py example to produce the plot below, and it seems like you're digitally inserting the FGSM attack directly into the data the eavesdropper receives, not adding it to your transmission pre-channel as in the paper this tutorial is associated with. Is there a simple way to do this with your API?
Best,
Kyle
Hi, this seems like it was a great tutorial section. The notebooks are very helpful, but do you happen to have any slides that include the intro portion of the talk?
I have downloaded the dataset, but encountered the following error when importing the dataset. How can I fix it?
ValueError Traceback (most recent call last)
Cell In[22], line 1
----> 1 dataset = load_RML201610A_dataset(path=data_path)
2 print(len(dataset))
3 pprint(dataset.get_examples_per_class())
File G:\xxxcode\rfml-master\notebooks..\rfml\data\converters\rml_2016.py:129, in load_RML201610A_dataset(path)
121 UNPICKLED_PATH = "RML2016.10a_dict.pkl"
123 loader = RML2016DataLoader(
124 cache_path=CACHE_PATH,
125 remote_url=REMOTE_URL,
126 unpickled_path=UNPICKLED_PATH,
127 warning_msg=WARNING_MSG,
128 )
--> 129 return loader.load(path=path)
File G:\xxxcode\rfml-master\notebooks..\rfml\data\converters\rml_2016.py:35, in RML2016DataLoader.load(self, path)
30 if not os.path.exists(path):
31 raise ValueError(
32 "If path is provided, it must actually exist. Provided path: "
33 "{}".format(path)
34 )
---> 35 return self._load_local(path=path)
37 # If this function has previously been called before to fetch the dataset from the
38 # remote, then it will have already been cached locally and unpickled.
39 if os.path.exists(self.UNPICKLED_PATH):
File G:\xxxcode\rfml-master\notebooks..\rfml\data\converters\rml_2016.py:53, in RML2016DataLoader._load_local(self, path)
51 for iq in data[(mod, snr)]:
52 builder.add(iq=iq, Modulation=mod, SNR=snr)
---> 53 return builder.build()
File G:\xxxcode\rfml-master\notebooks..\rfml\data\dataset_builder.py:156, in DatasetBuilder.build(self)
150 def build(self) -> Dataset:
151 """Build the Dataset based on the examples that have been added.
152
153 Returns:
154 Dataset: A compiled dataset consisting of the added examples.
155 """
--> 156 df = pd.DataFrame(self._rows, columns=self._keys)
157 return Dataset(df)
File G:\Users\xxx\anaconda3\envs\LYY2\Lib\site-packages\pandas\core\frame.py:675, in DataFrame.init(self, data, index, columns, dtype, copy)
673 raise ValueError("index cannot be a set")
674 if columns is not None and isinstance(columns, set):
--> 675 raise ValueError("columns cannot be a set")
677 if copy is None:
678 if isinstance(data, dict):
679 # retain pre-GH#38939 default behavior
ValueError: columns cannot be a set
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.