Release v0.3.1 (#109)

* Change README logo if in dark mode (#95)

* Start transform tests & minor `RandomTimeShift` optimization (#94)

* Start transform tests & slight optimization in RandomTimeShift

* Add new length check for TimeCrop tests

* Code style

* Fixed name mangling.

* QAM/PSK Pulse shaping filter transition bandwidth corrected (#98)

* excess bandwidth is defined in porportion to signal bandwidth, not sampling rate, thus needs to be scaled by the samples per symbol

* filling in a comment to describe modification to code

* QAM/PSK Pulse shaping filter transition bandwidth corrected (#98)

* excess bandwidth is defined in porportion to signal bandwidth, not sampling rate, thus needs to be scaled by the samples per symbol

* filling in a comment to describe modification to code

* OFDM Modulator filter lengths estimated and bandwidth randomized (#99)

* * cutoff frequency for LPF now randomized when using 'rand_lpf'
* derives a transition bandwidth from the cutoff frequency
* uses filter length approximating function for the randomized LPF

* using filter estimation function for pre-computed LPF taps

* Tests for visual inspection. (#103)

* 91 create generation performance benchmarks for each modulation type (#104)

* Initial benchmarking code.

* Some benchmarks

* Adding initial benchmarks.

* Fix action.

---------

* 75 examine ofdm generation for potential speedups for sig53 (#105)

* Tests for visual inspection of modulation generation. (#102)

* Optimizations show significant improvement in generation speed.

* Nominal behavior after using scipy.

* Adding initial Dockerfile (#108)

* Incrementing version

.github/workflows/pytest.yml

@@ -32,4 +32,5 @@ jobs:
       - name: Test with pytest
         run: |
           pip install pytest
-          pytest --ignore-glob=*_figures.py
+          pytest --ignore-glob=*_figures.py --ignore-glob=*_benchmark.py
+

.gitignore

@@ -10,3 +10,4 @@ checkpoints/
 lightning_logs/
 *.pt
 *.jpg
+*.benchmarks/

Dockerfile

@@ -0,0 +1,15 @@
+FROM pytorch/pytorch:1.13.1-cuda11.6-cudnn8-runtime
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+ADD torchsig/ /build/torchsig
+
+ADD pyproject.toml /build/pyproject.toml
+
+RUN pip3 install /build
+
+RUN pip3 install notebook
+
+WORKDIR /workspace/code
+
+ADD examples/ /workspace/code/examples

README.md

@@ -1,5 +1,8 @@
 <p align="center">
-  <img src="docs/logo.png" alt="drawing" width="500"/>
+    <picture>
+        <source media="(prefers-color-scheme: dark)" srcset="docs/torchsig_logo_white_dodgerblue.png">
+        <img src="docs/logo.png" width="500">
+    </picture>
 </p>
 
 -----
@@ -40,6 +43,17 @@ cd torchsig
 pip install .
 ```
 
+## Using the Dockerfile
+If you have Docker installed along with compatible GPUs and drivers, you can try:
+
+```
+docker build -t torchsig -f Dockerfile .
+docker run -d --rm --network=host --shm-size=32g --gpus all --name torchsig_workspace torchsig tail -f /dev/null
+docker exec torchsig_workspace jupyter notebook --allow-root --ip=0.0.0.0 --no-browser
+```
+
+Then use the URL in the output in your browser to run the examples and notebooks.
+
 ## License
 ---
 TorchSig is released under the MIT License. The MIT license is a popular open-source software license enabling free use, redistribution, and modifications, even for commercial purposes, provided the license is included in all copies or substantial portions of the software. TorchSig has no connection to MIT, other than through the use of this license.

pyproject.toml

@@ -12,7 +12,7 @@ readme = "README.md"
 requires-python = ">=3.7"
 license = {text = "MIT"}
 dependencies = [
-    "torch==1.13.0",
+    "torch==1.13.1",
     "torchvision",
     "tqdm",
     "numpy",

tests/test_modulation_benchmark.py

@@ -0,0 +1,69 @@
+from torchsig.datasets.synthetic import (
+    ConstellationDataset,
+    FSKDataset,
+    OFDMDataset,
+    default_const_map,
+    freq_map,
+)
+from matplotlib import pyplot as plt
+import numpy as np
+import pytest
+
+
+def iterate_one_epoch(dataset):
+    for _ in dataset:
+        pass
+
+
+@pytest.mark.benchmark(group="constellation")
+@pytest.mark.parametrize("modulation_name", default_const_map.keys())
+def test_generate_constellation_benchmark(benchmark, modulation_name):
+    dataset = ConstellationDataset(
+        [modulation_name],
+        num_iq_samples=4096,
+        num_samples_per_class=100,
+        iq_samples_per_symbol=2,
+        pulse_shape_filter=None,
+        random_pulse_shaping=False,
+        random_data=False,
+        use_gpu=False,
+    )
+    benchmark(iterate_one_epoch, dataset)
+
+
+@pytest.mark.benchmark(group="fsk")
+@pytest.mark.parametrize("modulation_name", freq_map.keys())
+def test_generate_fsk_benchmark(benchmark, modulation_name):
+    dataset = FSKDataset(
+        [modulation_name],
+        num_iq_samples=4096,
+        num_samples_per_class=100,
+        iq_samples_per_symbol=2,
+        random_pulse_shaping=False,
+        random_data=False,
+        use_gpu=False,
+    )
+    benchmark(iterate_one_epoch, dataset)
+
+
+num_subcarriers = (64, 72, 128, 180, 256, 300, 512, 600, 900, 1024, 1200, 2048)
+
+
+@pytest.mark.benchmark(group="ofdm")
+@pytest.mark.parametrize("num_subcarriers", num_subcarriers)
+def test_generate_ofdm_benchmark(benchmark, num_subcarriers):
+    constellations = ("bpsk", "qpsk", "16qam", "64qam", "256qam", "1024qam")
+    sidelobe_suppression_methods = ("lpf", "win_start")
+    dataset = OFDMDataset(
+        constellations,
+        num_subcarriers=(num_subcarriers,),
+        num_iq_samples=4096,
+        num_samples_per_class=100,
+        sidelobe_suppression_methods=sidelobe_suppression_methods,
+        use_gpu=False,
+    )
+    benchmark(iterate_one_epoch, dataset)
+
+
+if __name__ == "__main__":
+    pytest.main()

tests/test_transforms.py

@@ -0,0 +1,121 @@
+from unittest import TestCase
+from torchsig.transforms.system_impairment.si import RandomTimeShift, TimeCrop
+import numpy as np
+
+
+class RandomTimeShiftTestCase(TestCase):
+    def test_random_time_shift_right(self):
+        rng = np.random.RandomState(0)
+        data = (
+            rng.rand(
+                16,
+            )
+            - 0.5
+        ) + 1j * (
+            rng.rand(
+                16,
+            )
+            - 0.5
+        )
+        shift = 5
+        t = RandomTimeShift(
+            shift=shift,
+        )
+        new_data = t(data)
+        self.assertTrue(np.allclose(data[:-shift], new_data[shift:]))
+        self.assertTrue(np.allclose(new_data[:shift], np.zeros(shift)))
+
+    def test_random_time_shift_left(self):
+        rng = np.random.RandomState(0)
+        data = (
+            rng.rand(
+                16,
+            )
+            - 0.5
+        ) + 1j * (
+            rng.rand(
+                16,
+            )
+            - 0.5
+        )
+        shift = -5
+        t = RandomTimeShift(
+            shift=shift,
+        )
+        new_data = t(data)
+        self.assertTrue(np.allclose(data[-shift:], new_data[:shift]))
+        self.assertTrue(np.allclose(new_data[shift:], np.zeros(np.abs(shift))))
+
+
+class TimeCropTestCase(TestCase):
+    def test_time_crop_start(self):
+        rng = np.random.RandomState(0)
+        num_iq_samples = 16
+        data = (
+            rng.rand(
+                num_iq_samples,
+            )
+            - 0.5
+        ) + 1j * (
+            rng.rand(
+                num_iq_samples,
+            )
+            - 0.5
+        )
+        length = 4
+        t = TimeCrop(
+            crop_type="start",
+            length=length,
+        )
+        new_data: np.ndarray = t(data)
+        self.assertTrue(np.allclose(data[:length], new_data))
+        self.assertTrue(new_data.shape[0] == length)
+
+    def test_time_crop_center(self):
+        rng = np.random.RandomState(0)
+        num_iq_samples = 16
+        data = (
+            rng.rand(
+                num_iq_samples,
+            )
+            - 0.5
+        ) + 1j * (
+            rng.rand(
+                num_iq_samples,
+            )
+            - 0.5
+        )
+        length = 4
+        t = TimeCrop(
+            crop_type="center",
+            length=length,
+        )
+        new_data: np.ndarray = t(data)
+        extra_samples = num_iq_samples - length
+        self.assertTrue(
+            np.allclose(data[extra_samples // 2 : -extra_samples // 2], new_data)
+        )
+        self.assertTrue(new_data.shape[0] == length)
+
+    def test_time_crop_end(self):
+        rng = np.random.RandomState(0)
+        num_iq_samples = 16
+        data = (
+            rng.rand(
+                num_iq_samples,
+            )
+            - 0.5
+        ) + 1j * (
+            rng.rand(
+                num_iq_samples,
+            )
+            - 0.5
+        )
+        length = 4
+        t = TimeCrop(
+            crop_type="end",
+            length=length,
+        )
+        new_data: np.ndarray = t(data)
+        self.assertTrue(np.allclose(data[-length:], new_data))
+        self.assertTrue(new_data.shape[0] == length)

torchsig/__init__.py

@@ -1 +1 @@
-__version__ = "0.3.0"
+__version__ = "0.3.1"