From dfa43b4456506ed6946ab73b7f5be489e147fd82 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Sat, 14 Jan 2023 18:00:39 -0500
Subject: [PATCH 01/24] removed pillow

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 pyproject.toml   | 2 +-
 requirements.txt | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 51a3cb0..96c188f 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -11,7 +11,7 @@ name = "analogvnn"
 [project]
 # $ pip install analogvnn
 name = "analogvnn"
-version = "1.0.0rc6"
+version = "1.0.0rc7"
 description = "A fully modular framework for modeling and optimizing analog/photonic neural networks"  # Optional
 readme = "README.md"
 requires-python = ">=3.7"
diff --git a/requirements.txt b/requirements.txt
index 464c65c..49cef03 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -11,6 +11,5 @@ importlib-metadata<5.0.0,>=2.0.0; python_version < '3.8'
 tensorflow>=2.0.0
 tensorboard>=2.0.0
 torchinfo
-pillow
 # conda install graphviz
 graphviz

From a4be11c665e4fb01ae4181ff9df8500f142773be Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Sat, 14 Jan 2023 18:02:30 -0500
Subject: [PATCH 02/24] version fix

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index 49cef03..e87479b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,7 +5,7 @@ torchaudio
 numpy
 scipy
 networkx
-importlib-metadata<5.0.0,>=2.0.0; python_version < '3.8'
+importlib-metadata; python_version < '3.8'
 
 # Full
 tensorflow>=2.0.0

From 3f7cf26aaf2811507bb96086a4734a642307e34b Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Sat, 14 Jan 2023 19:45:05 -0500
Subject: [PATCH 03/24] name change gaussian_dirac_delta

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/fn/dirac_delta.py        | 10 +++++-----
 analogvnn/nn/noise/PoissonNoise.py |  4 ++--
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/analogvnn/fn/dirac_delta.py b/analogvnn/fn/dirac_delta.py
index 8e9f021..85a0317 100644
--- a/analogvnn/fn/dirac_delta.py
+++ b/analogvnn/fn/dirac_delta.py
@@ -2,19 +2,19 @@
 
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 
-__all__ = ['dirac_delta']
+__all__ = ['gaussian_dirac_delta']
 
 
-def dirac_delta(x: TENSOR_OPERABLE, a: TENSOR_OPERABLE = 0.001) -> TENSOR_OPERABLE:
-    """`dirac_delta` takes `x` and returns the Dirac delta function of `x` with standard deviation of `a`.
+def gaussian_dirac_delta(x: TENSOR_OPERABLE, std: TENSOR_OPERABLE = 0.001) -> TENSOR_OPERABLE:
+    """Gaussian Dirac Delta function with standard deviation `std`
 
     Args:
         x (TENSOR_OPERABLE): Tensor
-        a (TENSOR_OPERABLE): standard deviation.
+        std (TENSOR_OPERABLE): standard deviation.
 
     Returns:
         TENSOR_OPERABLE: TENSOR_OPERABLE with the same shape as x, but with values equal to the Dirac delta function
         of x.
     """
 
-    return 1 / (np.abs(a) * np.sqrt(np.pi)) * np.exp(-((x / a) ** 2))
+    return 1 / (np.abs(std) * np.sqrt(np.pi)) * np.exp(-((x / std) ** 2))
diff --git a/analogvnn/nn/noise/PoissonNoise.py b/analogvnn/nn/noise/PoissonNoise.py
index 39a14ad..8f5a42c 100644
--- a/analogvnn/nn/noise/PoissonNoise.py
+++ b/analogvnn/nn/noise/PoissonNoise.py
@@ -7,7 +7,7 @@
 from torch import Tensor, nn
 
 from analogvnn.backward.BackwardIdentity import BackwardIdentity
-from analogvnn.fn.dirac_delta import dirac_delta
+from analogvnn.fn.dirac_delta import gaussian_dirac_delta
 from analogvnn.nn.module.Layer import Layer
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 from analogvnn.utils.to_tensor_parameter import to_float_tensor, to_nongrad_parameter
@@ -219,7 +219,7 @@ def pdf(self, x: Tensor, rate: Tensor) -> Tensor:
         rate = rate if isinstance(rate, Tensor) else torch.tensor(rate, requires_grad=False)
 
         if torch.isclose(rate, torch.zeros_like(rate)):
-            return dirac_delta(x)
+            return gaussian_dirac_delta(x)
 
         return torch.exp(self.log_prob(x=x, rate=rate))
 

From 9cd16643d4a4de1cf2148d3e5c0b861d2872ca07 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Sat, 14 Jan 2023 19:46:27 -0500
Subject: [PATCH 04/24] update docs

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/fn/dirac_delta.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/analogvnn/fn/dirac_delta.py b/analogvnn/fn/dirac_delta.py
index 85a0317..1b9fe3d 100644
--- a/analogvnn/fn/dirac_delta.py
+++ b/analogvnn/fn/dirac_delta.py
@@ -13,8 +13,7 @@ def gaussian_dirac_delta(x: TENSOR_OPERABLE, std: TENSOR_OPERABLE = 0.001) -> TE
         std (TENSOR_OPERABLE): standard deviation.
 
     Returns:
-        TENSOR_OPERABLE: TENSOR_OPERABLE with the same shape as x, but with values equal to the Dirac delta function
-        of x.
+        TENSOR_OPERABLE: TENSOR_OPERABLE with the same shape as x, with values of the Gaussian Dirac Delta function.
     """
 
     return 1 / (np.abs(std) * np.sqrt(np.pi)) * np.exp(-((x / std) ** 2))

From e843f76820215d7f675625b6a47d19eb1bc9b241 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Tue, 17 Jan 2023 19:10:43 -0500
Subject: [PATCH 05/24] type hinting update

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/utils/is_cpu_cuda.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/analogvnn/utils/is_cpu_cuda.py b/analogvnn/utils/is_cpu_cuda.py
index 8d7d7c6..582b242 100644
--- a/analogvnn/utils/is_cpu_cuda.py
+++ b/analogvnn/utils/is_cpu_cuda.py
@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Tuple
+from typing import Tuple, Union
 
 import torch
 
@@ -47,11 +47,11 @@ def use_cuda_if_available(self) -> CPUCuda:
             self.set_device(f'cuda:{torch.cuda.current_device()}')
         return self
 
-    def set_device(self, device_name: str) -> CPUCuda:
+    def set_device(self, device_name: Union[str, torch.device]) -> CPUCuda:
         """Set the device to the given device name.
 
         Args:
-            device_name (str): the device name.
+            device_name (Union[str, torch.device]): the device name.
 
         Returns:
             CPUCuda: self

From 13fc6a81f93f906faf14beddde3a9cda876135ce Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Tue, 17 Jan 2023 19:21:04 -0500
Subject: [PATCH 06/24] updated docs

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 .flake8                     |  1 +
 analogvnn/__init__.py       |  3 ++-
 analogvnn/fn/dirac_delta.py |  2 +-
 pyproject.toml              | 12 ++++++------
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/.flake8 b/.flake8
index 4f02f5c..0078e18 100644
--- a/.flake8
+++ b/.flake8
@@ -6,6 +6,7 @@ extend-ignore =
     D100, # Missing docstring in public module
     D104, # Missing docstring in public package
     D202, # No blank lines allowed after function docstring
+    D210, # No whitespaces allowed surrounding docstring text
     D401, # First line should be in imperative mood
     R504, # unnecessary variable assignment before return statement
     R505, # unnecessary else after return statement
diff --git a/analogvnn/__init__.py b/analogvnn/__init__.py
index fb54294..2b82be5 100644
--- a/analogvnn/__init__.py
+++ b/analogvnn/__init__.py
@@ -1,3 +1,5 @@
+""" AnalogVNN: A fully modular framework for modeling and optimizing analog/photonic neural networks."""
+
 import sys
 
 if sys.version_info[:2] >= (3, 8):
@@ -5,7 +7,6 @@
 else:
     import importlib_metadata as metadata  # pragma: no cover
 
-
 __package__ = 'analogvnn'
 __author__ = 'Vivswan Shah (vivswanshah@pitt.edu)'
 
diff --git a/analogvnn/fn/dirac_delta.py b/analogvnn/fn/dirac_delta.py
index 1b9fe3d..31f493e 100644
--- a/analogvnn/fn/dirac_delta.py
+++ b/analogvnn/fn/dirac_delta.py
@@ -6,7 +6,7 @@
 
 
 def gaussian_dirac_delta(x: TENSOR_OPERABLE, std: TENSOR_OPERABLE = 0.001) -> TENSOR_OPERABLE:
-    """Gaussian Dirac Delta function with standard deviation `std`
+    """Gaussian Dirac Delta function with standard deviation `std`.
 
     Args:
         x (TENSOR_OPERABLE): Tensor
diff --git a/pyproject.toml b/pyproject.toml
index 96c188f..70225e2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -8,6 +8,9 @@ build-backend = "flit_core.buildapi"
 [tool.flit.module]
 name = "analogvnn"
 
+[tool.setuptools]
+py-modules = ['analogvnn']
+
 [project]
 # $ pip install analogvnn
 name = "analogvnn"
@@ -106,6 +109,7 @@ flake8 = [
     "flake8-deprecated",
 ]
 dev = [
+    "flit", # for building {flit build}
     "setuptools>=61.0.0",
     "build", # building the package {pyproject-build}
     "twine", # to publish on pypi {twine upload --repository-url=https://test.pypi.org/legacy/ dist/*} {twine upload dist/*}
@@ -113,6 +117,7 @@ dev = [
 ]
 test = ["analogvnn[flake8]"]
 all = ["analogvnn[full,dev,doc,test]"]
+
 [project.urls]
 "Author" = "https://vivswan.github.io/"
 "Bug Reports" = "https://github.com/Vivswan/AnalogVNN/issues"
@@ -124,9 +129,4 @@ all = ["analogvnn[full,dev,doc,test]"]
 # The following would provide a command line executable called `sample`
 # which executes the function `main` from this package when invoked.
 #[project.scripts]  # Optional
-#sample = "sample:main"
-
-# This is configuration specific to the `setuptools` build backend.
-# If you are using a different build backend, you will need to change this.
-[tool.setuptools]
-py-modules = ['analogvnn']
\ No newline at end of file
+#sample = "sample:main"
\ No newline at end of file

From a16cefad35f48487bb59227d1f35e9aa1ef0475d Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Tue, 17 Jan 2023 19:21:34 -0500
Subject: [PATCH 07/24] added flit

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 requirements/requirements-dev.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/requirements/requirements-dev.txt b/requirements/requirements-dev.txt
index 2a15cd3..30603a0 100644
--- a/requirements/requirements-dev.txt
+++ b/requirements/requirements-dev.txt
@@ -1,4 +1,5 @@
 # Development
+flit
 setuptools>=61.0.0
 build # building the package {pyproject-build}
 twine # to publish on pypi {twine upload --repository-url=https://test.pypi.org/legacy/ dist/*} {twine upload dist/*}

From 516cc595448e4ffdfec4e6ba43f7e2fb193ba28b Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Wed, 18 Jan 2023 23:43:12 -0500
Subject: [PATCH 08/24] added get_model_summaries

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/__init__.py                  |  2 +-
 analogvnn/fn/__init__.py               |  1 +
 analogvnn/utils/TensorboardModelLog.py | 34 +++-------------
 analogvnn/utils/get_model_summaries.py | 56 ++++++++++++++++++++++++++
 4 files changed, 63 insertions(+), 30 deletions(-)
 create mode 100644 analogvnn/utils/get_model_summaries.py

diff --git a/analogvnn/__init__.py b/analogvnn/__init__.py
index 2b82be5..667e237 100644
--- a/analogvnn/__init__.py
+++ b/analogvnn/__init__.py
@@ -1,4 +1,4 @@
-""" AnalogVNN: A fully modular framework for modeling and optimizing analog/photonic neural networks."""
+"""AnalogVNN: A fully modular framework for modeling and optimizing analog/photonic neural networks."""
 
 import sys
 
diff --git a/analogvnn/fn/__init__.py b/analogvnn/fn/__init__.py
index e69de29..4722389 100644
--- a/analogvnn/fn/__init__.py
+++ b/analogvnn/fn/__init__.py
@@ -0,0 +1 @@
+"""Additional functions for analogvnn."""
diff --git a/analogvnn/utils/TensorboardModelLog.py b/analogvnn/utils/TensorboardModelLog.py
index 5ee65aa..db25434 100644
--- a/analogvnn/utils/TensorboardModelLog.py
+++ b/analogvnn/utils/TensorboardModelLog.py
@@ -15,6 +15,8 @@
 
 __all__ = ['TensorboardModelLog']
 
+from analogvnn.utils.get_model_summaries import get_model_summaries
+
 
 class TensorboardModelLog:
     """Tensorboard model log.
@@ -162,45 +164,19 @@ def add_summary(
 
         Returns:
             Tuple[str, str]: the model __repr__ and the model summary.
-
-        Raises:
-            ImportError: if torchinfo (https://github.com/tyleryep/torchinfo) is not installed.
         """
 
-        try:
-            import torchinfo
-        except ImportError as e:
-            raise ImportError('requires torchinfo: https://github.com/tyleryep/torchinfo') from e
-
         if model is None:
             model = self.model
 
         log_id = f'{self.tensorboard.log_dir}_{TensorboardModelLog.add_summary.__name__}_{id(model)}'
 
-        if input_size is None:
-            data_shape = next(iter(train_loader))[0].shape
-            input_size = tuple(list(data_shape)[1:])
-
-        use_autograd_graph = False
-        if isinstance(model, Layer):
-            use_autograd_graph = model.use_autograd_graph
-            model.use_autograd_graph = True
-
-        nn_model_summary = torchinfo.summary(
-            model,
+        model_str, nn_model_summary = get_model_summaries(
+            model=model,
             input_size=input_size,
-            verbose=torchinfo.Verbosity.QUIET,
-            col_names=[e.value for e in torchinfo.ColumnSettings],
-            depth=10,
+            train_loader=train_loader
         )
 
-        if isinstance(model, Layer):
-            model.use_autograd_graph = use_autograd_graph
-
-        nn_model_summary.formatting.verbose = torchinfo.Verbosity.VERBOSE
-        model_str = str(model)
-        nn_model_summary = f'{nn_model_summary}'
-
         if log_id in self._log_record:
             return model_str, nn_model_summary
 
diff --git a/analogvnn/utils/get_model_summaries.py b/analogvnn/utils/get_model_summaries.py
new file mode 100644
index 0000000..c159840
--- /dev/null
+++ b/analogvnn/utils/get_model_summaries.py
@@ -0,0 +1,56 @@
+from typing import Optional, Sequence, Tuple
+
+from torch import nn
+from torch.utils.data import DataLoader
+
+from analogvnn.nn.module.Layer import Layer
+
+
+def get_model_summaries(
+        train_loader: DataLoader,
+        model: Optional[nn.Module] = None,
+        input_size: Optional[Sequence[int]] = None,
+) -> Tuple[str, str]:
+    """Creates the model summaries.
+
+    Args:
+        train_loader (DataLoader): the train loader.
+        model (nn.Module): the model to log.
+        input_size (Optional[Sequence[int]]): the input size.
+
+    Returns:
+        Tuple[str, str]: the model __repr__ and the model summary.
+
+    Raises:
+        ImportError: if torchinfo (https://github.com/tyleryep/torchinfo) is not installed.
+    """
+
+    try:
+        import torchinfo
+    except ImportError as e:
+        raise ImportError('requires torchinfo: https://github.com/tyleryep/torchinfo') from e
+
+    if input_size is None:
+        data_shape = next(iter(train_loader))[0].shape
+        input_size = tuple(list(data_shape)[1:])
+
+    use_autograd_graph = False
+    if isinstance(model, Layer):
+        use_autograd_graph = model.use_autograd_graph
+        model.use_autograd_graph = True
+
+    model_summary = torchinfo.summary(
+        model,
+        input_size=input_size,
+        verbose=torchinfo.Verbosity.QUIET,
+        col_names=[e.value for e in torchinfo.ColumnSettings],
+        depth=10,
+    )
+
+    if isinstance(model, Layer):
+        model.use_autograd_graph = use_autograd_graph
+
+    model_summary.formatting.verbose = torchinfo.Verbosity.VERBOSE
+    model_str = str(model)
+    model_summary = f'{model_summary}'
+    return model_str, model_summary

From bfff5a61d5c85ef081e9a9e69029c2ce54fd897b Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Wed, 18 Jan 2023 23:48:29 -0500
Subject: [PATCH 09/24] correction

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/utils/TensorboardModelLog.py | 6 +++---
 analogvnn/utils/get_model_summaries.py | 8 ++++++--
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/analogvnn/utils/TensorboardModelLog.py b/analogvnn/utils/TensorboardModelLog.py
index db25434..d2a032e 100644
--- a/analogvnn/utils/TensorboardModelLog.py
+++ b/analogvnn/utils/TensorboardModelLog.py
@@ -151,16 +151,16 @@ def add_graph(
 
     def add_summary(
             self,
-            train_loader: DataLoader,
-            model: Optional[nn.Module] = None,
+            model: Optional[nn.Module],
             input_size: Optional[Sequence[int]] = None,
+            train_loader: Optional[DataLoader] = None,
     ) -> Tuple[str, str]:
         """Add the model summary to the tensorboard.
 
         Args:
-            train_loader (DataLoader): the train loader.
             model (nn.Module): the model to log.
             input_size (Optional[Sequence[int]]): the input size.
+            train_loader (Optional[DataLoader]): the train loader.
 
         Returns:
             Tuple[str, str]: the model __repr__ and the model summary.
diff --git a/analogvnn/utils/get_model_summaries.py b/analogvnn/utils/get_model_summaries.py
index c159840..3c411ff 100644
--- a/analogvnn/utils/get_model_summaries.py
+++ b/analogvnn/utils/get_model_summaries.py
@@ -7,9 +7,9 @@
 
 
 def get_model_summaries(
-        train_loader: DataLoader,
-        model: Optional[nn.Module] = None,
+        model: Optional[nn.Module],
         input_size: Optional[Sequence[int]] = None,
+        train_loader: DataLoader = None,
 ) -> Tuple[str, str]:
     """Creates the model summaries.
 
@@ -23,6 +23,7 @@ def get_model_summaries(
 
     Raises:
         ImportError: if torchinfo (https://github.com/tyleryep/torchinfo) is not installed.
+        ValueError: if the input_size and train_loader are None.
     """
 
     try:
@@ -30,6 +31,9 @@ def get_model_summaries(
     except ImportError as e:
         raise ImportError('requires torchinfo: https://github.com/tyleryep/torchinfo') from e
 
+    if input_size is None and train_loader is None:
+        raise ValueError('input_size or train_loader must be provided')
+
     if input_size is None:
         data_shape = next(iter(train_loader))[0].shape
         input_size = tuple(list(data_shape)[1:])

From 76ac9bcf379d3655fdced52e01471be7cb5ab44a Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Thu, 19 Jan 2023 00:04:45 -0500
Subject: [PATCH 10/24] added args and kwargs

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/utils/TensorboardModelLog.py |  8 +++++++-
 analogvnn/utils/get_model_summaries.py | 16 +++++++++++++---
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/analogvnn/utils/TensorboardModelLog.py b/analogvnn/utils/TensorboardModelLog.py
index d2a032e..c1b9826 100644
--- a/analogvnn/utils/TensorboardModelLog.py
+++ b/analogvnn/utils/TensorboardModelLog.py
@@ -154,6 +154,8 @@ def add_summary(
             model: Optional[nn.Module],
             input_size: Optional[Sequence[int]] = None,
             train_loader: Optional[DataLoader] = None,
+            *args,
+            **kwargs
     ) -> Tuple[str, str]:
         """Add the model summary to the tensorboard.
 
@@ -161,6 +163,8 @@ def add_summary(
             model (nn.Module): the model to log.
             input_size (Optional[Sequence[int]]): the input size.
             train_loader (Optional[DataLoader]): the train loader.
+            *args: the arguments to torchinfo.summary.
+            **kwargs: the keyword arguments to torchinfo.summary.
 
         Returns:
             Tuple[str, str]: the model __repr__ and the model summary.
@@ -174,7 +178,9 @@ def add_summary(
         model_str, nn_model_summary = get_model_summaries(
             model=model,
             input_size=input_size,
-            train_loader=train_loader
+            train_loader=train_loader,
+            *args,
+            **kwargs
         )
 
         if log_id in self._log_record:
diff --git a/analogvnn/utils/get_model_summaries.py b/analogvnn/utils/get_model_summaries.py
index 3c411ff..a247c62 100644
--- a/analogvnn/utils/get_model_summaries.py
+++ b/analogvnn/utils/get_model_summaries.py
@@ -10,6 +10,8 @@ def get_model_summaries(
         model: Optional[nn.Module],
         input_size: Optional[Sequence[int]] = None,
         train_loader: DataLoader = None,
+        *args,
+        **kwargs
 ) -> Tuple[str, str]:
     """Creates the model summaries.
 
@@ -17,6 +19,8 @@ def get_model_summaries(
         train_loader (DataLoader): the train loader.
         model (nn.Module): the model to log.
         input_size (Optional[Sequence[int]]): the input size.
+        *args: the arguments to torchinfo.summary.
+        **kwargs: the keyword arguments to torchinfo.summary.
 
     Returns:
         Tuple[str, str]: the model __repr__ and the model summary.
@@ -43,12 +47,18 @@ def get_model_summaries(
         use_autograd_graph = model.use_autograd_graph
         model.use_autograd_graph = True
 
+    if 'depth' not in kwargs:
+        kwargs['depth'] = 10
+    if 'col_names' not in kwargs:
+        kwargs['col_names'] = (e.value for e in torchinfo.ColumnSettings)
+    if 'verbose' not in kwargs:
+        kwargs['verbose'] = torchinfo.Verbosity.QUIET
+
     model_summary = torchinfo.summary(
         model,
         input_size=input_size,
-        verbose=torchinfo.Verbosity.QUIET,
-        col_names=[e.value for e in torchinfo.ColumnSettings],
-        depth=10,
+        *args,
+        **kwargs,
     )
 
     if isinstance(model, Layer):

From 8534618f4c51c254f911511c4f4ef4515068ad83 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+vivswan@users.noreply.github.com>
Date: Thu, 19 Jan 2023 04:21:58 -0500
Subject: [PATCH 11/24] updated type hinting

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/backward/BackwardFunction.py | 23 +++++++++++------------
 analogvnn/nn/module/Model.py           | 12 ++++++------
 analogvnn/utils/common_types.py        | 10 +++++-----
 3 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/analogvnn/backward/BackwardFunction.py b/analogvnn/backward/BackwardFunction.py
index 73fc7b5..f653d29 100644
--- a/analogvnn/backward/BackwardFunction.py
+++ b/analogvnn/backward/BackwardFunction.py
@@ -1,12 +1,11 @@
 from __future__ import annotations
 
 from abc import ABC
-from typing import Callable
 
 from torch import nn, Tensor
 
 from analogvnn.backward.BackwardModule import BackwardModule
-from analogvnn.utils.common_types import TENSORS
+from analogvnn.utils.common_types import TENSORS, TENSOR_CALLABLE
 
 __all__ = ['BackwardFunction']
 
@@ -15,16 +14,16 @@ class BackwardFunction(BackwardModule, ABC):
     """The backward module that uses a function to compute the backward gradient.
 
     Attributes:
-        _backward_function (Callable): The function used to compute the backward gradient.
+        _backward_function (TENSOR_CALLABLE): The function used to compute the backward gradient.
     """
 
-    _backward_function: Callable
+    _backward_function: TENSOR_CALLABLE
 
-    def __init__(self, backward_function: Callable, layer: nn.Module = None):
+    def __init__(self, backward_function: TENSOR_CALLABLE, layer: nn.Module = None):
         """Initializes the backward module.
 
         Args:
-            backward_function (Callable): The function used to compute the backward gradient.
+            backward_function (TENSOR_CALLABLE): The function used to compute the backward gradient.
             layer (nn.Module): The layer that this backward module is associated with.
         """
 
@@ -32,30 +31,30 @@ def __init__(self, backward_function: Callable, layer: nn.Module = None):
         self._backward_function = backward_function
 
     @property
-    def backward_function(self) -> Callable:
+    def backward_function(self) -> TENSOR_CALLABLE:
         """The function used to compute the backward gradient.
 
         Returns:
-            Callable: The function used to compute the backward gradient.
+            TENSOR_CALLABLE: The function used to compute the backward gradient.
         """
 
         return self._backward_function
 
     @backward_function.setter
-    def backward_function(self, backward_function: Callable):
+    def backward_function(self, backward_function: TENSOR_CALLABLE):
         """Sets the function used to compute the backward gradient with.
 
         Args:
-            backward_function (Callable): The function used to compute the backward gradient with.
+            backward_function (TENSOR_CALLABLE): The function used to compute the backward gradient with.
         """
 
         self.set_backward_function(backward_function)
 
-    def set_backward_function(self, backward_function: Callable) -> BackwardFunction:
+    def set_backward_function(self, backward_function: TENSOR_CALLABLE) -> BackwardFunction:
         """Sets the function used to compute the backward gradient with.
 
         Args:
-            backward_function (Callable): The function used to compute the backward gradient with.
+            backward_function (TENSOR_CALLABLE): The function used to compute the backward gradient with.
 
         Returns:
             BackwardFunction: self.
diff --git a/analogvnn/nn/module/Model.py b/analogvnn/nn/module/Model.py
index ca93f1b..5c85f81 100644
--- a/analogvnn/nn/module/Model.py
+++ b/analogvnn/nn/module/Model.py
@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import typing
-from typing import Callable, Optional, Tuple, Set, Iterator
+from typing import Optional, Tuple, Set, Iterator
 
 import torch
 from torch import optim, Tensor, nn
@@ -13,7 +13,7 @@
 from analogvnn.graph.ForwardGraph import ForwardGraph
 from analogvnn.graph.ModelGraph import ModelGraph
 from analogvnn.nn.module.Layer import Layer
-from analogvnn.utils.common_types import TENSORS
+from analogvnn.utils.common_types import TENSORS, TENSOR_CALLABLE
 from analogvnn.utils.is_cpu_cuda import is_cpu_cuda
 
 if typing.TYPE_CHECKING:
@@ -32,8 +32,8 @@ class Model(Layer):
         forward_graph (ForwardGraph): The forward graph of the model.
         backward_graph (BackwardGraph): The backward graph of the model.
         optimizer (optim.Optimizer): The optimizer of the model.
-        loss_function (Callable): The loss function of the model.
-        accuracy_function (Callable): The accuracy function of the model.
+        loss_function (Optional[TENSOR_CALLABLE]): The loss function of the model.
+        accuracy_function (Optional[TENSOR_CALLABLE]): The accuracy function of the model.
         device (torch.device): The device of the model.
     """
 
@@ -48,8 +48,8 @@ class Model(Layer):
     backward_graph: BackwardGraph
 
     optimizer: Optional[optim.Optimizer]
-    loss_function: Optional[Callable]
-    accuracy_function: Optional[Callable]
+    loss_function: Optional[TENSOR_CALLABLE]
+    accuracy_function: Optional[TENSOR_CALLABLE]
     device: torch.device
 
     def __init__(self, tensorboard_log_dir=None, device=is_cpu_cuda.device):
diff --git a/analogvnn/utils/common_types.py b/analogvnn/utils/common_types.py
index 60028e4..1af7a57 100644
--- a/analogvnn/utils/common_types.py
+++ b/analogvnn/utils/common_types.py
@@ -4,11 +4,11 @@
 
 __all__ = ['TENSOR_OPERABLE', 'TENSOR_CALLABLE', 'TENSORS']
 
-TENSOR_OPERABLE = Union[Sequence[Tensor], Tensor, int, float, bool]
+TENSORS = Union[None, Tensor, Sequence[Tensor]]
+"""`TENSORS` is a type alias for a tensor or a sequence of tensors. """
+
+TENSOR_OPERABLE = Union[TENSORS, int, float, bool]
 """`TENSOR_OPERABLE` is a type alias for types that can be operated on by a tensor. """
 
-TENSOR_CALLABLE = Callable[[TENSOR_OPERABLE], TENSOR_OPERABLE]
+TENSOR_CALLABLE = Callable[[TENSOR_OPERABLE, ...], TENSOR_OPERABLE]
 """`TENSOR_CALLABLE` is a type alias for a function that takes a `TENSOR_OPERABLE` and returns a `TENSOR_OPERABLE`. """
-
-TENSORS = Union[None, Tensor, Sequence[Tensor]]
-"""`TENSORS` is a type alias for a tensor or a sequence of tensors. """

From 201ea9b341c73cf6ba9e50d8b59a9d5a4b31d7c0 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Thu, 19 Jan 2023 04:22:24 -0500
Subject: [PATCH 12/24] bug fix

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/utils/TensorboardModelLog.py |  4 ++--
 analogvnn/utils/get_model_summaries.py | 17 +++++++++++------
 sample_code_with_logs.py               |  4 ++--
 3 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/analogvnn/utils/TensorboardModelLog.py b/analogvnn/utils/TensorboardModelLog.py
index c1b9826..80b18c2 100644
--- a/analogvnn/utils/TensorboardModelLog.py
+++ b/analogvnn/utils/TensorboardModelLog.py
@@ -151,18 +151,18 @@ def add_graph(
 
     def add_summary(
             self,
-            model: Optional[nn.Module],
             input_size: Optional[Sequence[int]] = None,
             train_loader: Optional[DataLoader] = None,
+            model: Optional[nn.Module] = None,
             *args,
             **kwargs
     ) -> Tuple[str, str]:
         """Add the model summary to the tensorboard.
 
         Args:
-            model (nn.Module): the model to log.
             input_size (Optional[Sequence[int]]): the input size.
             train_loader (Optional[DataLoader]): the train loader.
+            model (nn.Module): the model to log.
             *args: the arguments to torchinfo.summary.
             **kwargs: the keyword arguments to torchinfo.summary.
 
diff --git a/analogvnn/utils/get_model_summaries.py b/analogvnn/utils/get_model_summaries.py
index a247c62..1fc72fa 100644
--- a/analogvnn/utils/get_model_summaries.py
+++ b/analogvnn/utils/get_model_summaries.py
@@ -35,12 +35,18 @@ def get_model_summaries(
     except ImportError as e:
         raise ImportError('requires torchinfo: https://github.com/tyleryep/torchinfo') from e
 
-    if input_size is None and train_loader is None:
+    if input_size is None and train_loader is None and 'input_size' not in kwargs:
         raise ValueError('input_size or train_loader must be provided')
 
-    if input_size is None:
-        data_shape = next(iter(train_loader))[0].shape
-        input_size = tuple(list(data_shape)[1:])
+    if 'input_size' not in kwargs:
+        if input_size is None:
+            data_shape = list(next(iter(train_loader))[0].shape)
+            if train_loader.batch_size > 0:
+                data_shape[0] = 1
+
+            input_size = data_shape
+
+        kwargs['input_size'] = input_size
 
     use_autograd_graph = False
     if isinstance(model, Layer):
@@ -50,13 +56,12 @@ def get_model_summaries(
     if 'depth' not in kwargs:
         kwargs['depth'] = 10
     if 'col_names' not in kwargs:
-        kwargs['col_names'] = (e.value for e in torchinfo.ColumnSettings)
+        kwargs['col_names'] = tuple(e.value for e in torchinfo.ColumnSettings)
     if 'verbose' not in kwargs:
         kwargs['verbose'] = torchinfo.Verbosity.QUIET
 
     model_summary = torchinfo.summary(
         model,
-        input_size=input_size,
         *args,
         **kwargs,
     )
diff --git a/sample_code_with_logs.py b/sample_code_with_logs.py
index acafa9c..61dce45 100644
--- a/sample_code_with_logs.py
+++ b/sample_code_with_logs.py
@@ -214,8 +214,8 @@ def run_linear3_model():
     nn_model.create_tensorboard(str(data_path.joinpath('tensorboard')))
 
     print('Saving Summary and Graphs...')
-    _, nn_model_summary = nn_model.tensorboard.add_summary(train_loader)
-    _, weight_model_summary = nn_model.tensorboard.add_summary(train_loader, model=weight_model)
+    _, nn_model_summary = nn_model.tensorboard.add_summary(train_loader=train_loader)
+    _, weight_model_summary = nn_model.tensorboard.add_summary(train_loader=train_loader, model=weight_model)
     save_autograd_graph_from_module(data_path.joinpath('nn_model'), nn_model, next(iter(train_loader))[0])
     save_autograd_graph_from_module(data_path.joinpath('weight_model'), weight_model, torch.ones((1, 1)))
     save_autograd_graph_from_module(

From b62ce3e8af6e92f04fa061ade7e752e98e08b204 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+vivswan@users.noreply.github.com>
Date: Thu, 19 Jan 2023 04:57:11 -0500
Subject: [PATCH 13/24] better type hinting

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/nn/noise/GaussianNoise.py                 | 4 ++--
 analogvnn/nn/noise/LaplacianNoise.py                | 4 ++--
 analogvnn/nn/noise/Noise.py                         | 7 +++++++
 analogvnn/nn/noise/PoissonNoise.py                  | 4 ++--
 analogvnn/nn/noise/UniformNoise.py                  | 4 ++--
 analogvnn/nn/normalize/Clamp.py                     | 5 +++--
 analogvnn/nn/normalize/LPNorm.py                    | 3 ++-
 analogvnn/nn/normalize/Normalize.py                 | 3 +--
 analogvnn/nn/precision/Precision.py                 | 7 +++++++
 analogvnn/nn/precision/ReducePrecision.py           | 4 ++--
 analogvnn/nn/precision/StochasticReducePrecision.py | 4 ++--
 11 files changed, 32 insertions(+), 17 deletions(-)
 create mode 100644 analogvnn/nn/noise/Noise.py
 create mode 100644 analogvnn/nn/precision/Precision.py

diff --git a/analogvnn/nn/noise/GaussianNoise.py b/analogvnn/nn/noise/GaussianNoise.py
index 4fe31bd..1041dab 100644
--- a/analogvnn/nn/noise/GaussianNoise.py
+++ b/analogvnn/nn/noise/GaussianNoise.py
@@ -7,14 +7,14 @@
 from torch import Tensor, nn
 
 from analogvnn.backward.BackwardIdentity import BackwardIdentity
-from analogvnn.nn.module.Layer import Layer
+from analogvnn.nn.noise.Noise import Noise
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 from analogvnn.utils.to_tensor_parameter import to_nongrad_parameter, to_float_tensor
 
 __all__ = ['GaussianNoise']
 
 
-class GaussianNoise(Layer, BackwardIdentity):
+class GaussianNoise(Noise, BackwardIdentity):
     """Implements the Gaussian noise function.
 
     Attributes:
diff --git a/analogvnn/nn/noise/LaplacianNoise.py b/analogvnn/nn/noise/LaplacianNoise.py
index ab2b00e..be6e98d 100644
--- a/analogvnn/nn/noise/LaplacianNoise.py
+++ b/analogvnn/nn/noise/LaplacianNoise.py
@@ -6,14 +6,14 @@
 from torch import Tensor, nn
 
 from analogvnn.backward.BackwardIdentity import BackwardIdentity
-from analogvnn.nn.module.Layer import Layer
+from analogvnn.nn.noise.Noise import Noise
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 from analogvnn.utils.to_tensor_parameter import to_float_tensor, to_nongrad_parameter
 
 __all__ = ['LaplacianNoise']
 
 
-class LaplacianNoise(Layer, BackwardIdentity):
+class LaplacianNoise(Noise, BackwardIdentity):
     """Implements the Laplacian noise function.
 
     Attributes:
diff --git a/analogvnn/nn/noise/Noise.py b/analogvnn/nn/noise/Noise.py
new file mode 100644
index 0000000..18b9095
--- /dev/null
+++ b/analogvnn/nn/noise/Noise.py
@@ -0,0 +1,7 @@
+from analogvnn.nn.module.Layer import Layer
+
+__all__ = ['Noise']
+
+
+class Noise(Layer):
+    """This class is base class for all noise functions."""
diff --git a/analogvnn/nn/noise/PoissonNoise.py b/analogvnn/nn/noise/PoissonNoise.py
index 8f5a42c..c42fe78 100644
--- a/analogvnn/nn/noise/PoissonNoise.py
+++ b/analogvnn/nn/noise/PoissonNoise.py
@@ -8,14 +8,14 @@
 
 from analogvnn.backward.BackwardIdentity import BackwardIdentity
 from analogvnn.fn.dirac_delta import gaussian_dirac_delta
-from analogvnn.nn.module.Layer import Layer
+from analogvnn.nn.noise.Noise import Noise
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 from analogvnn.utils.to_tensor_parameter import to_float_tensor, to_nongrad_parameter
 
 __all__ = ['PoissonNoise']
 
 
-class PoissonNoise(Layer, BackwardIdentity):
+class PoissonNoise(Noise, BackwardIdentity):
     """Implements the Poisson noise function.
 
     Attributes:
diff --git a/analogvnn/nn/noise/UniformNoise.py b/analogvnn/nn/noise/UniformNoise.py
index 7e73652..34445d2 100644
--- a/analogvnn/nn/noise/UniformNoise.py
+++ b/analogvnn/nn/noise/UniformNoise.py
@@ -4,14 +4,14 @@
 from torch import Tensor, nn
 
 from analogvnn.backward.BackwardIdentity import BackwardIdentity
-from analogvnn.nn.module.Layer import Layer
+from analogvnn.nn.noise.Noise import Noise
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 from analogvnn.utils.to_tensor_parameter import to_float_tensor, to_nongrad_parameter
 
 __all__ = ['UniformNoise']
 
 
-class UniformNoise(Layer, BackwardIdentity):
+class UniformNoise(Noise, BackwardIdentity):
     """Implements the uniform noise function.
 
     Attributes:
diff --git a/analogvnn/nn/normalize/Clamp.py b/analogvnn/nn/normalize/Clamp.py
index 7db26fc..ef64a10 100644
--- a/analogvnn/nn/normalize/Clamp.py
+++ b/analogvnn/nn/normalize/Clamp.py
@@ -3,12 +3,13 @@
 import torch
 from torch import Tensor
 
+from analogvnn.backward.BackwardIdentity import BackwardIdentity
 from analogvnn.nn.normalize.Normalize import Normalize
 
 __all__ = ['Clamp', 'Clamp01']
 
 
-class Clamp(Normalize):
+class Clamp(Normalize, BackwardIdentity):
     """Implements the clamp normalization function with range [-1, 1]."""
 
     @staticmethod
@@ -39,7 +40,7 @@ def backward(self, grad_output: Optional[Tensor]) -> Optional[Tensor]:
         return grad_output * grad
 
 
-class Clamp01(Normalize):
+class Clamp01(Normalize, BackwardIdentity):
     """Implements the clamp normalization function with range [0, 1]."""
 
     @staticmethod
diff --git a/analogvnn/nn/normalize/LPNorm.py b/analogvnn/nn/normalize/LPNorm.py
index 68cc2d5..d8b2d78 100644
--- a/analogvnn/nn/normalize/LPNorm.py
+++ b/analogvnn/nn/normalize/LPNorm.py
@@ -1,12 +1,13 @@
 import torch
 from torch import nn, Tensor
 
+from analogvnn.backward.BackwardIdentity import BackwardIdentity
 from analogvnn.nn.normalize.Normalize import Normalize
 
 __all__ = ['LPNorm', 'LPNormW', 'L1Norm', 'L2Norm', 'L1NormW', 'L2NormW', 'L1NormM', 'L2NormM', 'L1NormWM', 'L2NormWM']
 
 
-class LPNorm(Normalize):
+class LPNorm(Normalize, BackwardIdentity):
     """Implements the row-wise Lp normalization function.
 
     Attributes:
diff --git a/analogvnn/nn/normalize/Normalize.py b/analogvnn/nn/normalize/Normalize.py
index ea547cf..6d9bb7b 100644
--- a/analogvnn/nn/normalize/Normalize.py
+++ b/analogvnn/nn/normalize/Normalize.py
@@ -1,8 +1,7 @@
-from analogvnn.backward.BackwardIdentity import BackwardIdentity
 from analogvnn.nn.module.Layer import Layer
 
 __all__ = ['Normalize']
 
 
-class Normalize(Layer, BackwardIdentity):
+class Normalize(Layer):
     """This class is base class for all normalization functions."""
diff --git a/analogvnn/nn/precision/Precision.py b/analogvnn/nn/precision/Precision.py
new file mode 100644
index 0000000..eb95cff
--- /dev/null
+++ b/analogvnn/nn/precision/Precision.py
@@ -0,0 +1,7 @@
+from analogvnn.nn.module.Layer import Layer
+
+__all__ = ['Precision']
+
+
+class Precision(Layer):
+    """This class is base class for all precision functions."""
diff --git a/analogvnn/nn/precision/ReducePrecision.py b/analogvnn/nn/precision/ReducePrecision.py
index 207889a..bdf122e 100644
--- a/analogvnn/nn/precision/ReducePrecision.py
+++ b/analogvnn/nn/precision/ReducePrecision.py
@@ -3,13 +3,13 @@
 
 from analogvnn.backward.BackwardIdentity import BackwardIdentity
 from analogvnn.fn.reduce_precision import reduce_precision
-from analogvnn.nn.module.Layer import Layer
+from analogvnn.nn.precision.Precision import Precision
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 
 __all__ = ['ReducePrecision']
 
 
-class ReducePrecision(Layer, BackwardIdentity):
+class ReducePrecision(Precision, BackwardIdentity):
     """Implements the reduce precision function.
 
     Attributes:
diff --git a/analogvnn/nn/precision/StochasticReducePrecision.py b/analogvnn/nn/precision/StochasticReducePrecision.py
index dad532a..566021d 100644
--- a/analogvnn/nn/precision/StochasticReducePrecision.py
+++ b/analogvnn/nn/precision/StochasticReducePrecision.py
@@ -3,13 +3,13 @@
 
 from analogvnn.backward.BackwardIdentity import BackwardIdentity
 from analogvnn.fn.reduce_precision import stochastic_reduce_precision
-from analogvnn.nn.module.Layer import Layer
+from analogvnn.nn.precision.Precision import Precision
 from analogvnn.utils.common_types import TENSOR_OPERABLE
 
 __all__ = ['StochasticReducePrecision']
 
 
-class StochasticReducePrecision(Layer, BackwardIdentity):
+class StochasticReducePrecision(Precision, BackwardIdentity):
     """Implements the stochastic reduce precision function.
 
     Attributes:

From 17130f84c54ed797b5032d1c06b275d9f9d58fcb Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Thu, 19 Jan 2023 05:16:35 -0500
Subject: [PATCH 14/24] better repr

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/nn/precision/StochasticReducePrecision.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/analogvnn/nn/precision/StochasticReducePrecision.py b/analogvnn/nn/precision/StochasticReducePrecision.py
index 566021d..448006e 100644
--- a/analogvnn/nn/precision/StochasticReducePrecision.py
+++ b/analogvnn/nn/precision/StochasticReducePrecision.py
@@ -75,7 +75,7 @@ def extra_repr(self) -> str:
             str: string
         """
 
-        return f'precision={self.precision}'
+        return f'precision={int(self.precision)}'
 
     def forward(self, x: Tensor) -> Tensor:
         """Forward function of the StochasticReducePrecision module.

From 1b1755c9353ab93f58eea0d46e3518046bba41ce Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Thu, 19 Jan 2023 05:16:55 -0500
Subject: [PATCH 15/24] save alias for render.

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/graph/AcyclicDirectedGraph.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/analogvnn/graph/AcyclicDirectedGraph.py b/analogvnn/graph/AcyclicDirectedGraph.py
index f333918..ada2d39 100644
--- a/analogvnn/graph/AcyclicDirectedGraph.py
+++ b/analogvnn/graph/AcyclicDirectedGraph.py
@@ -448,3 +448,6 @@ def render(self, *args, real_label: bool = False, **kwargs) -> str:
         """
 
         return to_graphviz_digraph(self.graph, real_label=real_label).render(*args, **kwargs)
+
+    save = render
+    """Alias for render."""

From 4e13826b419fc96c301ba4ab9b49913bf30ee1ff Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Thu, 19 Jan 2023 05:20:48 -0500
Subject: [PATCH 16/24] fix bug

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/graph/to_graph_viz_digraph.py | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/analogvnn/graph/to_graph_viz_digraph.py b/analogvnn/graph/to_graph_viz_digraph.py
index 9f9ffd3..5c75318 100644
--- a/analogvnn/graph/to_graph_viz_digraph.py
+++ b/analogvnn/graph/to_graph_viz_digraph.py
@@ -23,15 +23,9 @@ def to_graphviz_digraph(from_graph: networkx.DiGraph, real_label: bool = False)
         graphviz.Digraph: the converted graph.
 
     Raises:
-        ImportError: if pygraphviz (https://pygraphviz.github.io/) is not available.
         ImportError: if graphviz (https://pygraphviz.github.io/) is not available.
     """
 
-    try:
-        # noinspection PyPackageRequirements
-        import pygraphviz  # noqa: F401
-    except ImportError as e:
-        raise ImportError('requires pygraphviz: https://pygraphviz.github.io/') from e
     try:
         from graphviz import Digraph
     except ImportError as e:

From a6c3639a22e47c3ad158f576a0d4a31e6a37b555 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Tue, 24 Jan 2023 12:44:59 -0500
Subject: [PATCH 17/24] type hinting fix

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/graph/to_graph_viz_digraph.py | 2 +-
 analogvnn/utils/common_types.py         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/analogvnn/graph/to_graph_viz_digraph.py b/analogvnn/graph/to_graph_viz_digraph.py
index 5c75318..60ae94a 100644
--- a/analogvnn/graph/to_graph_viz_digraph.py
+++ b/analogvnn/graph/to_graph_viz_digraph.py
@@ -30,6 +30,7 @@ def to_graphviz_digraph(from_graph: networkx.DiGraph, real_label: bool = False)
         from graphviz import Digraph
     except ImportError as e:
         raise ImportError('requires graphviz: https://pygraphviz.github.io/') from e
+
     strict = networkx.number_of_selfloops(from_graph) == 0 and not from_graph.is_multigraph()
     node_attr = {
         'style': 'filled',
@@ -44,7 +45,6 @@ def to_graphviz_digraph(from_graph: networkx.DiGraph, real_label: bool = False)
         name=from_graph.name,
         strict=strict,
         node_attr=node_attr,
-        graph_attr={'size': '12,12'},
         format='svg'
     )
 
diff --git a/analogvnn/utils/common_types.py b/analogvnn/utils/common_types.py
index 1af7a57..a0f0028 100644
--- a/analogvnn/utils/common_types.py
+++ b/analogvnn/utils/common_types.py
@@ -10,5 +10,5 @@
 TENSOR_OPERABLE = Union[TENSORS, int, float, bool]
 """`TENSOR_OPERABLE` is a type alias for types that can be operated on by a tensor. """
 
-TENSOR_CALLABLE = Callable[[TENSOR_OPERABLE, ...], TENSOR_OPERABLE]
+TENSOR_CALLABLE = Callable[[TENSOR_OPERABLE], TENSOR_OPERABLE]
 """`TENSOR_CALLABLE` is a type alias for a function that takes a `TENSOR_OPERABLE` and returns a `TENSOR_OPERABLE`. """

From 46c9f480d57f0cc935bc602f62f98b83b2b50051 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Tue, 24 Jan 2023 12:53:37 -0500
Subject: [PATCH 18/24] remove redundant parameter

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/nn/Linear.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/analogvnn/nn/Linear.py b/analogvnn/nn/Linear.py
index 445493e..c3bf95a 100644
--- a/analogvnn/nn/Linear.py
+++ b/analogvnn/nn/Linear.py
@@ -31,12 +31,11 @@ def forward(self, x: Tensor):
 
         return y
 
-    def backward(self, grad_output: Optional[Tensor], weight: Optional[Tensor] = None) -> Optional[Tensor]:
+    def backward(self, grad_output: Optional[Tensor]) -> Optional[Tensor]:
         """Backward pass of the linear layer.
 
         Args:
             grad_output (Optional[Tensor]): The gradient of the output.
-            weight (Optional[Tensor]): The weight of the layer.
 
         Returns:
             Optional[Tensor]: The gradient of the input.
@@ -44,7 +43,7 @@ def backward(self, grad_output: Optional[Tensor], weight: Optional[Tensor] = Non
 
         grad_output = to_matrix(grad_output)
 
-        weight = to_matrix(self.weight if weight is None else weight)
+        weight = to_matrix(self.weight)
         grad_input = grad_output @ weight
 
         self.set_grad_of(self.weight, torch.mm(grad_output.t(), self.inputs))

From 9143c809285f04970f101f2443faeb46635f255f Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Sun, 29 Jan 2023 04:46:10 -0500
Subject: [PATCH 19/24] Sequence to tuple or list

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/backward/BackwardModule.py     | 4 ++--
 analogvnn/graph/ArgsKwargs.py            | 4 ++--
 analogvnn/graph/ForwardGraph.py          | 4 ++--
 analogvnn/utils/render_autograd_graph.py | 8 ++++----
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/analogvnn/backward/BackwardModule.py b/analogvnn/backward/BackwardModule.py
index 6193a12..7f12bff 100644
--- a/analogvnn/backward/BackwardModule.py
+++ b/analogvnn/backward/BackwardModule.py
@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import abc
-from typing import Callable, Any, Optional, Sequence, Tuple, Type
+from typing import Callable, Any, Optional, Tuple, Type
 
 import torch
 from torch import nn, Tensor, autograd
@@ -69,7 +69,7 @@ def backward(ctx: Any, *grad_outputs: Tensor) -> Tuple[None, None, TENSORS]:
             backward_module: BackwardModule = ctx.backward_module
             results = backward_module._call_impl_backward(*grad_outputs)
 
-            if isinstance(results, Sequence):
+            if isinstance(results, (tuple, list)):
                 return (None, None, *results)
 
             return None, None, results
diff --git a/analogvnn/graph/ArgsKwargs.py b/analogvnn/graph/ArgsKwargs.py
index 0899ea4..56a58bb 100644
--- a/analogvnn/graph/ArgsKwargs.py
+++ b/analogvnn/graph/ArgsKwargs.py
@@ -48,7 +48,7 @@ def __init__(self, args=None, kwargs=None):
         if isinstance(args, tuple):
             args = list(args)
 
-        if not isinstance(args, List):
+        if not isinstance(args, list):
             args = [args]
 
         self.args = args
@@ -79,7 +79,7 @@ def to_args_kwargs_object(cls, outputs: ArgsKwargsInput) -> ArgsKwargs:
             pass
         elif isinstance(outputs, dict):
             outputs = cls(kwargs=outputs)
-        elif isinstance(outputs, tuple) and len(outputs) == 2 and isinstance(outputs[1], dict):
+        elif isinstance(outputs, (tuple, list)) and len(outputs) == 2 and isinstance(outputs[1], dict):
             outputs = cls(args=outputs[0], kwargs=outputs[1])
         else:
             outputs = cls(args=outputs)
diff --git a/analogvnn/graph/ForwardGraph.py b/analogvnn/graph/ForwardGraph.py
index f66882c..d394f58 100644
--- a/analogvnn/graph/ForwardGraph.py
+++ b/analogvnn/graph/ForwardGraph.py
@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Dict, Sequence
+from typing import Dict
 
 import torch
 from torch import Tensor
@@ -69,7 +69,7 @@ def calculate(
             ArgsKwargsOutput: Output of the graph
         """
 
-        if not isinstance(inputs, Sequence):
+        if not isinstance(inputs, (tuple, list)):
             inputs = (inputs,)
 
         if not self.graph_state.use_autograd_graph and is_training:
diff --git a/analogvnn/utils/render_autograd_graph.py b/analogvnn/utils/render_autograd_graph.py
index d2edf16..ca36e04 100644
--- a/analogvnn/utils/render_autograd_graph.py
+++ b/analogvnn/utils/render_autograd_graph.py
@@ -102,7 +102,7 @@ def get_fn_name(fn: Callable, show_attrs: bool, max_attr_chars: int) -> str:
         attr = attr[len(SAVED_PREFIX):]
         if torch.is_tensor(val):
             attrs[attr] = '[saved tensor]'
-        elif isinstance(val, Sequence) and any(torch.is_tensor(t) for t in val):
+        elif isinstance(val, (tuple, list)) and any(torch.is_tensor(t) for t in val):
             attrs[attr] = '[saved tensors]'
         else:
             attrs[attr] = str(val)
@@ -205,7 +205,7 @@ def inputs(self, inputs: Union[Tensor, Sequence[Tensor]]):
         if not inputs:
             return
 
-        if not isinstance(inputs, Sequence):
+        if not isinstance(inputs, (tuple, list)):
             inputs = (inputs,)
 
         for i, v in enumerate(inputs):
@@ -253,7 +253,7 @@ def outputs(self) -> Optional[Sequence[Tensor]]:
     @outputs.setter
     def outputs(self, outputs):
         self._called = True
-        if outputs is not None and not isinstance(outputs, Sequence):
+        if outputs is not None and not isinstance(outputs, (tuple, list)):
             outputs = (outputs,)
 
         self._outputs = outputs
@@ -504,7 +504,7 @@ def _add_grad_fn(link: Union[Tensor, Callable], autograd_dot: AutoGradDot) -> Op
                 autograd_dot.add_tensor(val, name=attr, fillcolor='orange')
                 continue
 
-            if isinstance(val, Sequence):
+            if isinstance(val, (tuple, list)):
                 for i, t in enumerate(val):
                     if not torch.is_tensor(t):
                         continue

From 9a38144abc8a7318b78eeeafa0806e5a245e7a83 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Tue, 31 Jan 2023 01:00:31 -0500
Subject: [PATCH 20/24] added license notice

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/utils/render_autograd_graph.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/analogvnn/utils/render_autograd_graph.py b/analogvnn/utils/render_autograd_graph.py
index ca36e04..504d5a5 100644
--- a/analogvnn/utils/render_autograd_graph.py
+++ b/analogvnn/utils/render_autograd_graph.py
@@ -1,3 +1,7 @@
+# The original snippet is licensed under the MIT License.
+# The following code is modified snippet from https://github.com/szagoruyko/pytorchviz/blob/master/torchviz/dot.py
+# to render the autograd graph of a module or a tensor for analogvnn.
+
 from __future__ import annotations
 
 import dataclasses

From 274b1d87f7ff058ec3bd7fc1b92572b7988bda8c Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Mon, 27 Feb 2023 05:12:32 -0500
Subject: [PATCH 21/24] Rewrite super() calls

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 .gitignore                                     |  3 ---
 analogvnn/backward/BackwardFunction.py         |  2 +-
 analogvnn/backward/BackwardModule.py           |  4 ++--
 analogvnn/graph/AccumulateGrad.py              |  2 +-
 analogvnn/graph/AcyclicDirectedGraph.py        |  2 +-
 analogvnn/graph/ArgsKwargs.py                  |  2 +-
 analogvnn/graph/ModelGraph.py                  |  2 +-
 analogvnn/graph/ModelGraphState.py             |  2 +-
 analogvnn/nn/Linear.py                         |  2 +-
 analogvnn/nn/activation/ELU.py                 |  4 ++--
 analogvnn/nn/activation/Identity.py            |  2 +-
 analogvnn/nn/activation/ReLU.py                |  6 +++---
 analogvnn/nn/module/Layer.py                   |  4 ++--
 analogvnn/nn/module/Model.py                   |  6 +++---
 analogvnn/nn/noise/GaussianNoise.py            |  2 +-
 analogvnn/nn/noise/LaplacianNoise.py           |  2 +-
 analogvnn/nn/noise/PoissonNoise.py             |  2 +-
 analogvnn/nn/noise/UniformNoise.py             |  2 +-
 analogvnn/nn/normalize/LPNorm.py               | 18 +++++++++---------
 analogvnn/nn/precision/ReducePrecision.py      |  2 +-
 .../nn/precision/StochasticReducePrecision.py  |  2 +-
 analogvnn/parameter/Parameter.py               |  6 +++---
 analogvnn/parameter/PseudoParameter.py         |  4 ++--
 analogvnn/utils/TensorboardModelLog.py         |  2 +-
 analogvnn/utils/is_cpu_cuda.py                 |  2 +-
 docs/_static/AnalogVNN_Demo.ipynb              |  4 ++--
 docs/tutorial.md                               |  4 ++--
 sample_code.py                                 |  4 ++--
 sample_code_with_logs.py                       |  4 ++--
 unit_tests/test_pseudo_parameter.py            |  8 ++++----
 30 files changed, 54 insertions(+), 57 deletions(-)

diff --git a/.gitignore b/.gitignore
index 169fee3..480233d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,9 +3,6 @@ __pycache__/
 *.py[cod]
 *$py.class
 
-_run_files/
-_crc_slurm/
-_results/
 _data/
 .idea
 .idea/**
diff --git a/analogvnn/backward/BackwardFunction.py b/analogvnn/backward/BackwardFunction.py
index f653d29..41ee035 100644
--- a/analogvnn/backward/BackwardFunction.py
+++ b/analogvnn/backward/BackwardFunction.py
@@ -27,7 +27,7 @@ def __init__(self, backward_function: TENSOR_CALLABLE, layer: nn.Module = None):
             layer (nn.Module): The layer that this backward module is associated with.
         """
 
-        super(BackwardFunction, self).__init__(layer)
+        super().__init__(layer)
         self._backward_function = backward_function
 
     @property
diff --git a/analogvnn/backward/BackwardModule.py b/analogvnn/backward/BackwardModule.py
index 7f12bff..ec6c4a1 100644
--- a/analogvnn/backward/BackwardModule.py
+++ b/analogvnn/backward/BackwardModule.py
@@ -81,7 +81,7 @@ def __init__(self, layer: nn.Module = None):
             layer (nn.Module): The layer for which the backward gradient is computed.
         """
 
-        super(BackwardModule, self).__init__()
+        super().__init__()
         self._layer = None
         self._set_autograd_backward()
         if not isinstance(self, nn.Module):
@@ -282,7 +282,7 @@ def __getattr__(self, name: str) -> Any:
         """
 
         if isinstance(self, nn.Module) or self == self._layer:
-            return super(BackwardModule, self).__getattr__(name)
+            return super().__getattr__(name)
         if not str(name).startswith('__') and self._layer is not None and hasattr(self._layer, name):
             return getattr(self._layer, name)
         raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, name))
diff --git a/analogvnn/graph/AccumulateGrad.py b/analogvnn/graph/AccumulateGrad.py
index 4451250..2c7a0b3 100644
--- a/analogvnn/graph/AccumulateGrad.py
+++ b/analogvnn/graph/AccumulateGrad.py
@@ -30,7 +30,7 @@ def __init__(self, module: Union[nn.Module, Callable]):
             module (Union[nn.Module, Callable]): Module from which to accumulate gradients.
         """
 
-        super(AccumulateGrad, self).__init__()
+        super().__init__()
         self.input_output_connections = {}
         self.module = module
 
diff --git a/analogvnn/graph/AcyclicDirectedGraph.py b/analogvnn/graph/AcyclicDirectedGraph.py
index ada2d39..d13d705 100644
--- a/analogvnn/graph/AcyclicDirectedGraph.py
+++ b/analogvnn/graph/AcyclicDirectedGraph.py
@@ -50,7 +50,7 @@ def __init__(self, graph_state: ModelGraphState = None):
             NotImplementedError: If allow_loops is True, since this is not implemented yet.
         """
 
-        super(AcyclicDirectedGraph, self).__init__()
+        super().__init__()
         self.graph = nx.MultiDiGraph()
         self.graph_state = graph_state
         self._is_static = False
diff --git a/analogvnn/graph/ArgsKwargs.py b/analogvnn/graph/ArgsKwargs.py
index 56a58bb..7164006 100644
--- a/analogvnn/graph/ArgsKwargs.py
+++ b/analogvnn/graph/ArgsKwargs.py
@@ -39,7 +39,7 @@ def __init__(self, args=None, kwargs=None):
             kwargs: The keyword arguments.
         """
 
-        super(ArgsKwargs, self).__init__()
+        super().__init__()
         if args is None:
             args = []
         if kwargs is None:
diff --git a/analogvnn/graph/ModelGraph.py b/analogvnn/graph/ModelGraph.py
index a14b5fd..b04e3f0 100644
--- a/analogvnn/graph/ModelGraph.py
+++ b/analogvnn/graph/ModelGraph.py
@@ -26,7 +26,7 @@ def __init__(self, use_autograd_graph: bool = False, allow_loops: bool = False):
             allow_loops: If True, the graph is allowed to contain loops.
         """
 
-        super(ModelGraph, self).__init__(use_autograd_graph, allow_loops)
+        super().__init__(use_autograd_graph, allow_loops)
         self.forward_graph = ForwardGraph(self)
         self.backward_graph = BackwardGraph(self)
 
diff --git a/analogvnn/graph/ModelGraphState.py b/analogvnn/graph/ModelGraphState.py
index 9021cab..c33b44a 100644
--- a/analogvnn/graph/ModelGraphState.py
+++ b/analogvnn/graph/ModelGraphState.py
@@ -46,7 +46,7 @@ def __init__(self, use_autograd_graph: bool = False, allow_loops=False):
             allow_loops: If True, the graph is allowed to contain loops.
         """
 
-        super(ModelGraphState, self).__init__()
+        super().__init__()
         self.allow_loops = allow_loops
         self.use_autograd_graph = use_autograd_graph
 
diff --git a/analogvnn/nn/Linear.py b/analogvnn/nn/Linear.py
index c3bf95a..f8338b1 100644
--- a/analogvnn/nn/Linear.py
+++ b/analogvnn/nn/Linear.py
@@ -76,7 +76,7 @@ def __init__(self, in_features: int, out_features: int, bias: bool = True):
             bias (bool): True if the layer has a bias.
         """
 
-        super(Linear, self).__init__()
+        super().__init__()
         self.in_features = in_features
         self.out_features = out_features
 
diff --git a/analogvnn/nn/activation/ELU.py b/analogvnn/nn/activation/ELU.py
index 03cabce..4c28265 100644
--- a/analogvnn/nn/activation/ELU.py
+++ b/analogvnn/nn/activation/ELU.py
@@ -28,7 +28,7 @@ def __init__(self, alpha: float = 1.0507, scale_factor: float = 1.):
             scale_factor (float): the scale factor parameter.
         """
 
-        super(SELU, self).__init__()
+        super().__init__()
         self.alpha = nn.Parameter(torch.tensor(alpha), requires_grad=False)
         self.scale_factor = nn.Parameter(torch.tensor(scale_factor), requires_grad=False)
 
@@ -103,4 +103,4 @@ def __init__(self, alpha: float = 1.0507):
             alpha (float): the alpha parameter.
         """
 
-        super(ELU, self).__init__(alpha=alpha, scale_factor=1.)
+        super().__init__(alpha=alpha, scale_factor=1.)
diff --git a/analogvnn/nn/activation/Identity.py b/analogvnn/nn/activation/Identity.py
index 136741d..39853b9 100644
--- a/analogvnn/nn/activation/Identity.py
+++ b/analogvnn/nn/activation/Identity.py
@@ -23,7 +23,7 @@ def __init__(self, name=None):
             name (str): the name of the activation function.
         """
 
-        super(Identity, self).__init__()
+        super().__init__()
         self.name = name
 
     def extra_repr(self) -> str:
diff --git a/analogvnn/nn/activation/ReLU.py b/analogvnn/nn/activation/ReLU.py
index c7358f9..f735e7c 100644
--- a/analogvnn/nn/activation/ReLU.py
+++ b/analogvnn/nn/activation/ReLU.py
@@ -28,7 +28,7 @@ def __init__(self, alpha: float):
             alpha (float): the slope of the negative part of the activation function.
         """
 
-        super(PReLU, self).__init__()
+        super().__init__()
         self.alpha = nn.Parameter(torch.tensor(alpha), requires_grad=False)
         self._zero = nn.Parameter(torch.tensor(0), requires_grad=False)
 
@@ -95,7 +95,7 @@ class ReLU(PReLU):
     def __init__(self):
         """Initialize the rectified linear unit (ReLU) activation function."""
 
-        super(ReLU, self).__init__(alpha=0)
+        super().__init__(alpha=0)
 
     @staticmethod
     def initialise(tensor: Tensor) -> Tensor:
@@ -134,4 +134,4 @@ class LeakyReLU(PReLU):
     def __init__(self):
         """Initialize the leaky rectified linear unit (LeakyReLU) activation function."""
 
-        super(LeakyReLU, self).__init__(alpha=0.01)
+        super().__init__(alpha=0.01)
diff --git a/analogvnn/nn/module/Layer.py b/analogvnn/nn/module/Layer.py
index f73630e..97e20ce 100644
--- a/analogvnn/nn/module/Layer.py
+++ b/analogvnn/nn/module/Layer.py
@@ -79,7 +79,7 @@ class Layer(nn.Module):
 
     def __init__(self):
         """Initializes the layer."""
-        super(Layer, self).__init__()
+        super().__init__()
         self._inputs = None
         self._outputs = None
         self._backward_module = None
@@ -95,7 +95,7 @@ def __call__(self, *inputs, **kwargs):
         """
 
         self._forward_wrapper(self.forward)
-        outputs = super(Layer, self).__call__(*inputs, **kwargs)
+        outputs = super().__call__(*inputs, **kwargs)
         if self.training:
             self._inputs = ArgsKwargs(args=inputs, kwargs=kwargs)
             self._outputs = outputs
diff --git a/analogvnn/nn/module/Model.py b/analogvnn/nn/module/Model.py
index 5c85f81..20b919c 100644
--- a/analogvnn/nn/module/Model.py
+++ b/analogvnn/nn/module/Model.py
@@ -60,7 +60,7 @@ def __init__(self, tensorboard_log_dir=None, device=is_cpu_cuda.device):
             device (torch.device): The device to run the model on.
         """
 
-        super(Model, self).__init__()
+        super().__init__()
 
         self._compiled = False
 
@@ -94,7 +94,7 @@ def __call__(self, *args, **kwargs):
         if not self._compiled:
             raise RuntimeError('Model is not compiled yet.')
 
-        return super(Model, self).__call__(*args, **kwargs)
+        return super().__call__(*args, **kwargs)
 
     @property
     def use_autograd_graph(self):
@@ -139,7 +139,7 @@ def named_registered_children(
         memo.add(self.optimizer)
         memo.add(self.loss_function)
         memo.add(self.accuracy_function)
-        return super(Model, self).named_registered_children(memo=memo)
+        return super().named_registered_children(memo=memo)
 
     def compile(self, device: Optional[torch.device] = None, layer_data: bool = True):
         """Compile the model.
diff --git a/analogvnn/nn/noise/GaussianNoise.py b/analogvnn/nn/noise/GaussianNoise.py
index 1041dab..370ab9c 100644
--- a/analogvnn/nn/noise/GaussianNoise.py
+++ b/analogvnn/nn/noise/GaussianNoise.py
@@ -42,7 +42,7 @@ def __init__(
             precision (int): the precision of the Gaussian noise.
         """
 
-        super(GaussianNoise, self).__init__()
+        super().__init__()
 
         if (std is None) + (leakage is None) + (precision is None) != 1:
             raise ValueError('only 2 out of 3 arguments are needed (std, leakage, precision)')
diff --git a/analogvnn/nn/noise/LaplacianNoise.py b/analogvnn/nn/noise/LaplacianNoise.py
index be6e98d..98b8b5d 100644
--- a/analogvnn/nn/noise/LaplacianNoise.py
+++ b/analogvnn/nn/noise/LaplacianNoise.py
@@ -41,7 +41,7 @@ def __init__(
             precision (int): the precision of the Laplacian noise.
         """
 
-        super(LaplacianNoise, self).__init__()
+        super().__init__()
 
         if (scale is None) + (leakage is None) + (precision is None) != 1:
             raise ValueError('only 2 out of 3 arguments are needed (scale, leakage, precision)')
diff --git a/analogvnn/nn/noise/PoissonNoise.py b/analogvnn/nn/noise/PoissonNoise.py
index c42fe78..35e8f42 100644
--- a/analogvnn/nn/noise/PoissonNoise.py
+++ b/analogvnn/nn/noise/PoissonNoise.py
@@ -43,7 +43,7 @@ def __init__(
             precision (Optional[int]): the precision of the Poisson noise.
         """
 
-        super(PoissonNoise, self).__init__()
+        super().__init__()
 
         if (scale is None) + (max_leakage is None) + (precision is None) != 1:
             raise ValueError('only 2 out of 3 arguments are needed (scale, max_leakage, precision)')
diff --git a/analogvnn/nn/noise/UniformNoise.py b/analogvnn/nn/noise/UniformNoise.py
index 34445d2..e7d0a9b 100644
--- a/analogvnn/nn/noise/UniformNoise.py
+++ b/analogvnn/nn/noise/UniformNoise.py
@@ -43,7 +43,7 @@ def __init__(
             precision (int): the precision of the uniform noise.
         """
 
-        super(UniformNoise, self).__init__()
+        super().__init__()
 
         if (low is None or high is None) + (leakage is None) + (precision is None) != 1:
             raise ValueError('only 2 out of 3 arguments are needed (scale, leakage, precision)')
diff --git a/analogvnn/nn/normalize/LPNorm.py b/analogvnn/nn/normalize/LPNorm.py
index d8b2d78..1f6ec44 100644
--- a/analogvnn/nn/normalize/LPNorm.py
+++ b/analogvnn/nn/normalize/LPNorm.py
@@ -27,7 +27,7 @@ def __init__(self, p: int, make_max_1=False):
             make_max_1 (bool): if True, the maximum absolute value of the output tensor will be 1.
         """
 
-        super(LPNorm, self).__init__()
+        super().__init__()
         self.p = nn.Parameter(torch.tensor(p), requires_grad=False)
         self.make_max_1 = nn.Parameter(torch.tensor(make_max_1), requires_grad=False)
 
@@ -84,7 +84,7 @@ class L1Norm(LPNorm):
     def __init__(self):
         """Initializes the row-wise L1 normalization function."""
 
-        super(L1Norm, self).__init__(p=1, make_max_1=False)
+        super().__init__(p=1, make_max_1=False)
 
 
 class L2Norm(LPNorm):
@@ -93,7 +93,7 @@ class L2Norm(LPNorm):
     def __init__(self):
         """Initializes the row-wise L2 normalization function."""
 
-        super(L2Norm, self).__init__(p=2, make_max_1=False)
+        super().__init__(p=2, make_max_1=False)
 
 
 class L1NormW(LPNormW):
@@ -102,7 +102,7 @@ class L1NormW(LPNormW):
     def __init__(self):
         """Initializes the whole matrix L1 normalization function."""
 
-        super(L1NormW, self).__init__(p=1, make_max_1=False)
+        super().__init__(p=1, make_max_1=False)
 
 
 class L2NormW(LPNormW):
@@ -111,7 +111,7 @@ class L2NormW(LPNormW):
     def __init__(self):
         """Initializes the whole matrix L2 normalization function."""
 
-        super(L2NormW, self).__init__(p=2, make_max_1=False)
+        super().__init__(p=2, make_max_1=False)
 
 
 class L1NormM(LPNorm):
@@ -120,7 +120,7 @@ class L1NormM(LPNorm):
     def __init__(self):
         """Initializes the row-wise L1 normalization function with maximum absolute value of 1."""
 
-        super(L1NormM, self).__init__(p=1, make_max_1=True)
+        super().__init__(p=1, make_max_1=True)
 
 
 class L2NormM(LPNorm):
@@ -129,7 +129,7 @@ class L2NormM(LPNorm):
     def __init__(self):
         """Initializes the row-wise L2 normalization function with maximum absolute value of 1."""
 
-        super(L2NormM, self).__init__(p=2, make_max_1=True)
+        super().__init__(p=2, make_max_1=True)
 
 
 class L1NormWM(LPNormW):
@@ -138,7 +138,7 @@ class L1NormWM(LPNormW):
     def __init__(self):
         """Initializes the whole matrix L1 normalization function with maximum absolute value of 1."""
 
-        super(L1NormWM, self).__init__(p=1, make_max_1=True)
+        super().__init__(p=1, make_max_1=True)
 
 
 class L2NormWM(LPNormW):
@@ -147,4 +147,4 @@ class L2NormWM(LPNormW):
     def __init__(self):
         """Initializes the whole matrix L2 normalization function with maximum absolute value of 1."""
 
-        super(L2NormWM, self).__init__(p=2, make_max_1=True)
+        super().__init__(p=2, make_max_1=True)
diff --git a/analogvnn/nn/precision/ReducePrecision.py b/analogvnn/nn/precision/ReducePrecision.py
index bdf122e..16476cb 100644
--- a/analogvnn/nn/precision/ReducePrecision.py
+++ b/analogvnn/nn/precision/ReducePrecision.py
@@ -31,7 +31,7 @@ def __init__(self, precision: int = None, divide: float = 0.5):
              then 0.6 will be rounded to 1.0 and 0.4 will be rounded to 0.0.
         """
 
-        super(ReducePrecision, self).__init__()
+        super().__init__()
         if precision < 1:
             raise ValueError(f'precision has to be more than 0, but got {precision}')
 
diff --git a/analogvnn/nn/precision/StochasticReducePrecision.py b/analogvnn/nn/precision/StochasticReducePrecision.py
index 448006e..5bc6e27 100644
--- a/analogvnn/nn/precision/StochasticReducePrecision.py
+++ b/analogvnn/nn/precision/StochasticReducePrecision.py
@@ -26,7 +26,7 @@ def __init__(self, precision: int = 8):
             precision (int): the precision of the output tensor.
         """
 
-        super(StochasticReducePrecision, self).__init__()
+        super().__init__()
         if precision < 1:
             raise ValueError('precision has to be more than 0, but got {}'.format(precision))
 
diff --git a/analogvnn/parameter/Parameter.py b/analogvnn/parameter/Parameter.py
index 2999efe..be337e5 100644
--- a/analogvnn/parameter/Parameter.py
+++ b/analogvnn/parameter/Parameter.py
@@ -22,7 +22,7 @@ def __new__(cls, data=None, requires_grad=True, *args, **kwargs):
             Parameter: the created parameter.
         """
 
-        return super(Parameter, cls).__new__(cls, data, requires_grad)
+        return super().__new__(cls, data, requires_grad)
 
     # noinspection PyUnusedLocal
     def __init__(self, data=None, requires_grad=True, *args, **kwargs):
@@ -35,7 +35,7 @@ def __init__(self, data=None, requires_grad=True, *args, **kwargs):
             **kwargs: additional keyword arguments.
         """
 
-        super(Parameter, self).__init__()
+        super().__init__()
 
     def __repr__(self, *args, **kwargs):
         """Returns a string representation of the parameter.
@@ -48,4 +48,4 @@ def __repr__(self, *args, **kwargs):
             str: the string representation.
         """
 
-        return super(Parameter, self).__repr__(*args, **kwargs)
+        return super().__repr__(*args, **kwargs)
diff --git a/analogvnn/parameter/PseudoParameter.py b/analogvnn/parameter/PseudoParameter.py
index 5b14945..2118e6f 100644
--- a/analogvnn/parameter/PseudoParameter.py
+++ b/analogvnn/parameter/PseudoParameter.py
@@ -32,7 +32,7 @@ def __init__(self, original, transformed):
             transformed (nn.Parameter): the transformed parameters.
         """
 
-        super(PseudoParameterModule, self).__init__()
+        super().__init__()
         self.original = original
         self._transformed = transformed
 
@@ -125,7 +125,7 @@ def __init__(self, data=None, requires_grad=True, transformation=None, *args, **
             **kwargs: additional keyword arguments.
         """
 
-        super(PseudoParameter, self).__init__(data, requires_grad, *args, **kwargs)
+        super().__init__(data, requires_grad, *args, **kwargs)
         self._transformed = nn.Parameter(data=data, requires_grad=requires_grad)
         self._transformed.original = self
         self._transformation = self.identity
diff --git a/analogvnn/utils/TensorboardModelLog.py b/analogvnn/utils/TensorboardModelLog.py
index 80b18c2..283b7f0 100644
--- a/analogvnn/utils/TensorboardModelLog.py
+++ b/analogvnn/utils/TensorboardModelLog.py
@@ -41,7 +41,7 @@ def __init__(self, model: Model, log_dir: str):
             log_dir (str): the directory to log to.
         """
 
-        super(TensorboardModelLog, self).__init__()
+        super().__init__()
         self.model = model
         self.tensorboard = None
         self.layer_data = True
diff --git a/analogvnn/utils/is_cpu_cuda.py b/analogvnn/utils/is_cpu_cuda.py
index 582b242..e56fb16 100644
--- a/analogvnn/utils/is_cpu_cuda.py
+++ b/analogvnn/utils/is_cpu_cuda.py
@@ -21,7 +21,7 @@ class CPUCuda:
     def __init__(self):
         """Initialize the CPUCuda class."""
 
-        super(CPUCuda, self).__init__()
+        super().__init__()
         self._device = None
         self.device_name = None
         self.use_cpu()
diff --git a/docs/_static/AnalogVNN_Demo.ipynb b/docs/_static/AnalogVNN_Demo.ipynb
index 09adbe0..0111b2b 100644
--- a/docs/_static/AnalogVNN_Demo.ipynb
+++ b/docs/_static/AnalogVNN_Demo.ipynb
@@ -209,7 +209,7 @@
    "source": [
     "class LinearModel(FullSequential):\n",
     "    def __init__(self, activation_class, norm_class, precision_class, precision, noise_class, leakage):\n",
-    "        super(LinearModel, self).__init__()\n",
+    "        super().__init__()\n",
     "\n",
     "        self.activation_class = activation_class\n",
     "        self.norm_class = norm_class\n",
@@ -289,7 +289,7 @@
    "source": [
     "class WeightModel(FullSequential):\n",
     "    def __init__(self, norm_class, precision_class, precision, noise_class, leakage):\n",
-    "        super(WeightModel, self).__init__()\n",
+    "        super().__init__()\n",
     "        self.all_layers = []\n",
     "\n",
     "        self.all_layers.append(norm_class())\n",
diff --git a/docs/tutorial.md b/docs/tutorial.md
index 5c4d7da..f8017c1 100644
--- a/docs/tutorial.md
+++ b/docs/tutorial.md
@@ -16,7 +16,7 @@ To convert a digital model to its analog counterpart the following steps needs t
         ```python
         class LinearModel(FullSequential):
             def __init__(self, activation_class, norm_class, precision_class, precision, noise_class, leakage):
-                super(LinearModel, self).__init__()
+                super().__init__()
 
                 self.activation_class = activation_class
                 self.norm_class = norm_class
@@ -55,7 +55,7 @@ To convert a digital model to its analog counterpart the following steps needs t
     ```python
     class WeightModel(FullSequential):
         def __init__(self, norm_class, precision_class, precision, noise_class, leakage):
-            super(WeightModel, self).__init__()
+            super().__init__()
             self.all_layers = []
 
             self.all_layers.append(norm_class())
diff --git a/sample_code.py b/sample_code.py
index b4bc9c1..652f7f4 100644
--- a/sample_code.py
+++ b/sample_code.py
@@ -93,7 +93,7 @@ def __init__(self, activation_class, norm_class, precision_class, precision, noi
             the analog channel).
         """
 
-        super(LinearModel, self).__init__()
+        super().__init__()
 
         self.activation_class = activation_class
         self.norm_class = norm_class
@@ -143,7 +143,7 @@ def __init__(self, norm_class, precision_class, precision, noise_class, leakage)
             the analog channel).
         """
 
-        super(WeightModel, self).__init__()
+        super().__init__()
         self.all_layers = []
 
         self.all_layers.append(norm_class())
diff --git a/sample_code_with_logs.py b/sample_code_with_logs.py
index 61dce45..b1356cc 100644
--- a/sample_code_with_logs.py
+++ b/sample_code_with_logs.py
@@ -96,7 +96,7 @@ def __init__(self, activation_class, norm_class, precision_class, precision, noi
             the analog channel).
         """
 
-        super(LinearModel, self).__init__()
+        super().__init__()
 
         self.activation_class = activation_class
         self.norm_class = norm_class
@@ -146,7 +146,7 @@ def __init__(self, norm_class, precision_class, precision, noise_class, leakage)
             the analog channel).
         """
 
-        super(WeightModel, self).__init__()
+        super().__init__()
         self.all_layers = []
 
         self.all_layers.append(norm_class())
diff --git a/unit_tests/test_pseudo_parameter.py b/unit_tests/test_pseudo_parameter.py
index 726d5ef..3b50d89 100644
--- a/unit_tests/test_pseudo_parameter.py
+++ b/unit_tests/test_pseudo_parameter.py
@@ -9,19 +9,19 @@
 
 # def __getattribute__(self, item):
 #     print(f"__getattribute__:: {item!r}")
-#     return super(PseudoParameter, self).__getattribute__(item)
+#     return super().__getattribute__(item)
 #
 # def __setattr__(self, key, value):
 #     print(f"__setattr__:: {key!r} -> {value!r}")
-#     super(PseudoParameter, self).__setattr__(key, value)
+#     super().__setattr__(key, value)
 #
 # # def __set__(self, instance, value):
 # #     print(f"__set__:: {instance!r} -> {value!r}")
-# #     super(PseudoParameter, self).__set__(instance, value)
+# #     super().__set__(instance, value)
 #
 # def __get__(self, instance, owner):
 #     print(f"__get__:: {instance!r} -> {owner!r}")
-#     return super(PseudoParameter, self).__get__(instance, owner)
+#     return super().__get__(instance, owner)
 #
 # @classmethod
 # def __torch_function__(cls, func, types, args=(), kwargs=None):

From f866e884cdab45b176b59786388acab139ca1ab9 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Mon, 27 Feb 2023 05:14:42 -0500
Subject: [PATCH 22/24] using f-strings

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/backward/BackwardModule.py                | 2 +-
 analogvnn/nn/precision/StochasticReducePrecision.py | 4 ++--
 analogvnn/utils/render_autograd_graph.py            | 2 +-
 docs/conf.py                                        | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/analogvnn/backward/BackwardModule.py b/analogvnn/backward/BackwardModule.py
index ec6c4a1..9de8dd1 100644
--- a/analogvnn/backward/BackwardModule.py
+++ b/analogvnn/backward/BackwardModule.py
@@ -285,4 +285,4 @@ def __getattr__(self, name: str) -> Any:
             return super().__getattr__(name)
         if not str(name).startswith('__') and self._layer is not None and hasattr(self._layer, name):
             return getattr(self._layer, name)
-        raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, name))
+        raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")
diff --git a/analogvnn/nn/precision/StochasticReducePrecision.py b/analogvnn/nn/precision/StochasticReducePrecision.py
index 5bc6e27..981587e 100644
--- a/analogvnn/nn/precision/StochasticReducePrecision.py
+++ b/analogvnn/nn/precision/StochasticReducePrecision.py
@@ -28,10 +28,10 @@ def __init__(self, precision: int = 8):
 
         super().__init__()
         if precision < 1:
-            raise ValueError('precision has to be more than 0, but got {}'.format(precision))
+            raise ValueError(f'precision has to be more than 0, but got {precision}')
 
         if precision != int(precision):
-            raise ValueError('precision must be int, but got {}'.format(precision))
+            raise ValueError(f'precision must be int, but got {precision}')
 
         self.precision = nn.Parameter(torch.tensor(precision), requires_grad=False)
 
diff --git a/analogvnn/utils/render_autograd_graph.py b/analogvnn/utils/render_autograd_graph.py
index 504d5a5..a8a1ef3 100644
--- a/analogvnn/utils/render_autograd_graph.py
+++ b/analogvnn/utils/render_autograd_graph.py
@@ -755,7 +755,7 @@ def parse_trace_graph(graph) -> List[Node]:
             scope[inputs[i]] = n.scopeName()
 
         uname = next(n.outputs()).uniqueName()
-        assert n.scopeName() != '', '{} has empty scope name'.format(n)
+        assert n.scopeName() != '', f'{n} has empty scope name'
         scope[uname] = n.scopeName()
 
     scope['0'] = 'input'
diff --git a/docs/conf.py b/docs/conf.py
index 2b192a0..c838169 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -4,14 +4,14 @@
 try:
     from analogvnn import __version__
 
-    print('Version from module: {}'.format(__version__))
+    print(f'Version from module: {__version__}')
 except Exception:
     with open('../pyproject.toml', 'r') as f:
         for i in f.readlines():
             if 'version' in i:
                 __version__ = i.split('=')[1].strip().strip('"')
                 break
-    print('Version from toml: {}'.format(__version__))
+    print(f'Version from toml: {__version__}')
 
 # Configuration file for the Sphinx documentation builder.
 #

From 70c5afb81e366ba7f64b13f44b614b354938b762 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Mon, 27 Feb 2023 05:16:54 -0500
Subject: [PATCH 23/24] small correction to rewrite super() calls

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 analogvnn/backward/BackwardModule.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/analogvnn/backward/BackwardModule.py b/analogvnn/backward/BackwardModule.py
index 9de8dd1..f771002 100644
--- a/analogvnn/backward/BackwardModule.py
+++ b/analogvnn/backward/BackwardModule.py
@@ -282,7 +282,7 @@ def __getattr__(self, name: str) -> Any:
         """
 
         if isinstance(self, nn.Module) or self == self._layer:
-            return super().__getattr__(name)
+            return super(BackwardModule, self).__getattr__(name)
         if not str(name).startswith('__') and self._layer is not None and hasattr(self._layer, name):
             return getattr(self._layer, name)
         raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")

From 1919e391ea3fa9090ff9c8f04d97d3861cf4b960 Mon Sep 17 00:00:00 2001
From: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
Date: Tue, 7 Mar 2023 05:55:05 -0500
Subject: [PATCH 24/24] completed v1.0.0

Signed-off-by: Vivswan Shah <58091053+Vivswan@users.noreply.github.com>
---
 pyproject.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyproject.toml b/pyproject.toml
index 70225e2..9929739 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -14,7 +14,7 @@ py-modules = ['analogvnn']
 [project]
 # $ pip install analogvnn
 name = "analogvnn"
-version = "1.0.0rc7"
+version = "1.0.0"
 description = "A fully modular framework for modeling and optimizing analog/photonic neural networks"  # Optional
 readme = "README.md"
 requires-python = ">=3.7"