sinabs 3.0.4.dev25__py3-none-any.whl → 3.1.1__py3-none-any.whl

sinabs/network.py

@@ -4,6 +4,8 @@ from typing import Dict, List, Optional, Tuple, Union
 import numpy as np
 import torch
 import torch.nn as nn
+import pylab
+
 
 from .layers import StatefulLayer
 from .synopcounter import SNNAnalyzer
@@ -136,8 +138,6 @@ class Network(torch.nn.Module):
                 - ann_activity: output activity of the ann layers
                 - snn_activity: output activity of the snn layers
         """
-        import pylab
-
         analog_activations, spike_rates, name_list = self.compare_activations(
             data, name_list=name_list, compute_rate=compute_rate
         )
@@ -162,16 +162,18 @@ class Network(torch.nn.Module):
     ):
         """Reset all neuron states in the submodules.
 
-        Parameters
-        ----------
-        randomize: Bool
-            If true, reset the states between a range provided. Else, the states are reset to zero.
-        value_ranges: Optional[List[Dict[str, Tuple[float, float]]]]
-            A list of value_range dictionaries with the same length as the total stateful layers in the module.
-            Each dictionary is a key value pair: buffer_name -> (min, max) for each state that needs to be reset.
-            The states are reset with a uniform distribution between the min and max values specified.
-            Any state with an undefined key in this dictionary will be reset between 0 and 1
-            This parameter is only used if randomize is set to true.
+        Args:
+            randomize (bool): If true, reset the states between a range
+                provided. Else, the states are reset to zero.
+            value_ranges (Optional[List[Dict[str, Tuple[float, float]]]]): A
+                list of value_range dictionaries with the same length as the
+                total stateful layers in the module. Each dictionary is a key
+                value pair: buffer_name -> (min, max) for each state that needs
+                to be reset.
+                The states are reset with a uniform distribution between the min
+                and max values specified. Any state with an undefined key in
+                this dictionary will be reset between 0 and 1.
+                This parameter is only used if randomize is set to true.
         """
 
         if value_ranges:

sinabs/nir.py

@@ -46,8 +46,8 @@ def _import_sinabs_module(
             groups=node.groups,
             bias=True,
         )
-        conv.weight.data = torch.tensor(node.weight).float()
-        conv.bias.data = torch.tensor(node.bias).float()
+        conv.weight.data = node.weight.detach().clone().to(float)
+        conv.bias.data = node.bias.detach().clone().to(float)
         return conv
 
     elif isinstance(node, nir.Conv2d):
@@ -184,6 +184,7 @@ def _extract_sinabs_module(module: torch.nn.Module) -> Optional[nir.NIRNode]:
             return nir.Affine(module.weight.detach(), module.bias.detach())
     elif isinstance(module, torch.nn.Conv1d):
         return nir.Conv1d(
+            input_shape=None,
             weight=module.weight.detach(),
             stride=module.stride,
             padding=module.padding,
@@ -191,7 +192,7 @@ def _extract_sinabs_module(module: torch.nn.Module) -> Optional[nir.NIRNode]:
             groups=module.groups,
             bias=(
                 module.bias.detach()
-                if module.bias
+                if isinstance(module.bias, torch.Tensor)
                 else torch.zeros((module.weight.shape[0]))
             ),
         )

sinabs/synopcounter.py

@@ -90,7 +90,7 @@ class SNNAnalyzer:
     can therefore calculate the number of synaptic operations accurately for each layer by
     multiplying the respective connection map with the output.
 
-    Parameters:
+    Args:
         model: Your PyTorch model.
         dt: the number of milliseconds corresponding to a time step in the simulation (default 1.0).
 
@@ -151,8 +151,9 @@ class SNNAnalyzer:
     def get_layer_statistics(self, average: bool = False) -> dict:
         """Outputs a dictionary with statistics for each individual layer.
 
-        Parameters:
-            average (bool): The statistics such as firing rate per neuron, the number of neurons or synops are averaged across batches.
+        Args:
+            average (bool): The statistics such as firing rate per neuron, the number of neurons
+                or synops are averaged across batches.
         """
         spike_dict = {}
         spike_dict["spiking"] = {}
@@ -221,8 +222,9 @@ class SNNAnalyzer:
     def get_model_statistics(self, average: bool = False) -> dict:
         """Outputs a dictionary with statistics that are summarised across all layers.
 
-        Parameters:
-            average (bool): The statistics such as firing rate per neuron or synops are averaged across batches.
+        Args:
+            average (bool): The statistics such as firing rate per neuron or
+                synops are averaged across batches.
         """
         stats_dict = {}
         firing_rates = []
@@ -262,9 +264,10 @@ class SynOpCounter:
     """Counter for the synaptic operations emitted by all Neuromorphic ReLUs in an analog CNN
     model.
 
-    Parameters:
+    Args:
         modules: list of modules, e.g. MyTorchModel.modules()
-        sum_activations: If True (default), returns a single number of synops, otherwise a list of layer synops.
+        sum_activations: If True (default), returns a single number of synops,
+            otherwise a list of layer synops.
 
     Example:
         >>> counter = SynOpCounter(MyTorchModel.modules(), sum_activations=True)

sinabs/utils.py

@@ -1,4 +1,4 @@
-from typing import List, Tuple
+from typing import Iterable, List, Sequence, Tuple, TypeVar, Union
 
 import numpy as np
 import torch
@@ -8,10 +8,33 @@ import sinabs
 from .validate_memory_speck import ValidateMapping
 
 
+def get_new_index(existing_indices: Sequence) -> int:
+    """Get a new index that is not yet part of a Sequence of existing indices
+
+    Example:
+    `get_new_index([0,1,2,3])`: `4`
+    `get_new_index([0,1,3])`: `2`
+
+    Args:
+        existing_indices: Sequence of indices
+
+    Returns:
+        Smallest positive integer number (starting from 0) that is not yet in
+            `existing_indices`.
+    """
+    existing_indices = set(existing_indices)
+    # Largest possible index is the length of `existing_indices`, if they are
+    # consecutively numbered. Otherwise, if there is a "gap", this would be
+    # filled by a smaller number.
+    possible_indices = range(len(existing_indices) + 1)
+    unused_indices = existing_indices.symmetric_difference(possible_indices)
+    return min(unused_indices)
+
+
 def reset_states(model: nn.Module) -> None:
     """Helper function to recursively reset all states of spiking layers within the model.
 
-    Parameters:
+    Args:
         model: The torch module
     """
     for layer in model.children():
@@ -24,7 +47,7 @@ def reset_states(model: nn.Module) -> None:
 def zero_grad(model: nn.Module) -> None:
     """Helper function to recursively zero the gradients of all spiking layers within the model.
 
-    Parameters:
+    Args:
         model: The torch module
     """
     for layer in model.children():
@@ -80,7 +103,7 @@ def get_network_activations(
 ) -> List[np.ndarray]:
     """Returns the activity of neurons in each layer of the network.
 
-    Parameters:
+    Args:
         model: Model for which the activations are to be read out
         inp: Input to the model
         bRate: If true returns the rate, else returns spike count
@@ -130,13 +153,14 @@ def normalize_weights(
     `Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification` by Rueckauer et al.
     https://www.frontiersin.org/article/10.3389/fnins.2017.00682
 
-    Parameters:
+    Args:
          ann: Torch module
          sample_data: Input data to normalize the network with
-         output_layers: List of layers to verify activity of normalization. Typically this is a relu layer
+         output_layers: List of layers to verify activity of normalization.
+            Typically this is a relu layer.
          param_layers: List of layers whose parameters preceed `output_layers`
          percentile: A number between 0 and 100 to determine activity to be normalized by
-                     where a 100 corresponds to the max activity of the network. Defaults to 99.
+            where a 100 corresponds to the max activity of the network. Defaults to 99.
     """
     # Network activity storage
     output_data = []
@@ -182,6 +206,130 @@ def set_batch_size(model: nn.Module, batch_size: int):
             # reset_states(mod)
 
 
+def get_batch_size(model: nn.Module) -> int:
+    """Get batch size from any model with sinabs squeeze layers
+
+    Will raise a ValueError if different squeeze layers within the model
+    have different batch sizes. Ignores layers with batch size `-1`, if
+    others provide it.
+
+    Args:
+        model (nn.Module): pytorch model with sinabs Squeeze layers
+
+    Returns:
+        batch_size (int): The batch size, `-1` if none is found.
+    """
+
+    batch_sizes = {
+        mod.batch_size
+        for mod in model.modules()
+        if isinstance(mod, sinabs.layers.SqueezeMixin)
+    }
+    # Ignore values `-1` and `None`
+    batch_sizes.discard(-1)
+    batch_sizes.discard(None)
+
+    if len(batch_sizes) == 0:
+        return -1
+    elif len(batch_sizes) == 1:
+        return batch_sizes.pop()
+    else:
+        raise ValueError(
+            "The model contains layers with different batch sizes: "
+            ", ".join((str(s) for s in batch_sizes))
+        )
+
+
+def get_num_timesteps(model: nn.Module) -> int:
+    """Get number of timesteps from any model with sinabs squeeze layers
+
+    Will raise a ValueError if different squeeze layers within the model
+    have different `num_timesteps` attributes. Ignores layers with value
+    `-1`, if others provide it.
+
+    Args:
+        model (nn.Module): pytorch model with sinabs Squeeze layers
+
+    Returns:
+        num_timesteps (int): The number of time steps, `-1` if none is found.
+    """
+
+    numbers = {
+        mod.num_timesteps
+        for mod in model.modules()
+        if isinstance(mod, sinabs.layers.SqueezeMixin)
+    }
+    # Ignore values `-1` and `None`
+    numbers.discard(-1)
+    numbers.discard(None)
+
+    if len(numbers) == 0:
+        return -1
+    elif len(numbers) == 1:
+        return numbers.pop()
+    else:
+        raise ValueError(
+            "The model contains layers with different numbers of time steps: "
+            ", ".join((str(s) for s in numbers))
+        )
+
+
+def get_smallest_compatible_time_dimension(model: nn.Module) -> int:
+    """Find the smallest size for input to a model with sinabs squeeze layers
+    along the batch/time (first) dimension.
+
+    Will raise a ValueError if different squeeze layers within the model
+    have different `num_timesteps` or `batch_size` attributes (except for
+    `-1`)
+
+    Args:
+        model (nn.Module): pytorch model with sinabs Squeeze layers
+
+    Returns:
+        int: The smallest compatible size for the first dimension of
+            an input to the `model`.
+    """
+    batch_size = abs(get_batch_size(model))  # Use `abs` to turn -1 to 1
+    num_timesteps = abs(get_num_timesteps(model))
+    # Use `abs` to turn `-1` to `1`
+    return abs(batch_size * num_timesteps)
+
+
+def expand_to_pair(value) -> Tuple[int, int]:
+    """Expand a given value to a pair (tuple) if an int is passed.
+
+    Args:
+        value (int):
+    Returns:
+        pair: (int, int)
+    """
+    return (value, value) if isinstance(value, int) else value
+
+
+T = TypeVar("T")
+
+
+def collapse_pair(pair: Union[Iterable[T], T]) -> T:
+    """Collapse an iterable of equal elements by returning only the first
+
+    Args:
+        pair: Iterable. All elements should be the same.
+
+    Returns:
+        First item of `pair`. If `pair` is not iterable it will return `pair` itself.
+
+    Raises:
+        ValueError if not all elements in `pair` are equal.
+    """
+    if isinstance(pair, Iterable):
+        items = [x for x in pair]
+        if any(x != items[0] for x in items):
+            raise ValueError("All elements of `pair` must be the same")
+        return items[0]
+    else:
+        return pair
+
+
 def validate_memory_mapping_speck(
     input_feature_size: int,
     output_feature_size: int,

sinabs/validate_memory_speck.py

@@ -1,7 +1,4 @@
 from typing import Tuple
-from matplotlib import pyplot as plt
-from matplotlib import colors
-
 import numpy as np
 
 
@@ -66,8 +63,6 @@ class ValidateMapping:
             "neuron", neuron_memory, "kernel", kernel_memory
         )
 
-        print(kernel_error_msg)
-        print(neuron_error_msg)
         return (
             kernel_memory / 1024,
             neuron_memory / 1024,

{sinabs-3.0.4.dev25.dist-info → sinabs-3.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinabs
-Version: 3.0.4.dev25
+Version: 3.1.1
 Summary: SynSense Spiking Neural Network simulator for deep neural networks (DNNs).
 Author: SynSense (formerly AiCTX)
 Author-email: support@synsense.ai
@@ -23,6 +23,7 @@ Requires-Dist: torch>=1.8
 Requires-Dist: nir<=1.0.4
 Requires-Dist: nirtorch
 Requires-Dist: samna>=0.33
+Requires-Dist: matplotlib
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -86,7 +87,7 @@ Sinabs is published under Apache v2.0. See the LICENSE file for details.
 
 Contributing to Sinabs
 ------------------------
-Checkout the [contributing](https://sinabs.readthedocs.io/en/develop/about/contributing.html) page for more info.
+Checkout the [contributing](https://sinabs.readthedocs.io/develop/about/contributing.html) page for more info.
 
 
 Citation

sinabs-3.1.1.dist-info/RECORD

@@ -0,0 +1,65 @@
+sinabs/__init__.py,sha256=vvWzU_lrsSob2JpOdG7ok8Rm0FjR-v7ogYgK6zruAGk,458
+sinabs/cnnutils.py,sha256=MTVTmTnLYMiDQZozfgH7UhMCYQPpOto0vDa0kMjADiA,2406
+sinabs/conversion.py,sha256=wEACb-IMrsNcjoNvGjoaQSINHYs66j0XOeQSmk7nhTM,2011
+sinabs/from_torch.py,sha256=_jVoGP3aQcdCUIc39ujxhCQmbIDlDtzLHz6VY3zmX-k,5777
+sinabs/hooks.py,sha256=u6bzKXodhUHDLi_ZaUNbD8hogRX7RD4QoRouSUaKEzY,15962
+sinabs/network.py,sha256=Zn7fQ0WTU_7vgBwfVloGINrXivZTNIBsmUGLWAbX81A,9542
+sinabs/nir.py,sha256=LUUlWbV2jXJPWby5SoHFl0_c5tMVaQlsw-U_s-WjecY,8761
+sinabs/synopcounter.py,sha256=VFefA5ix0JqCr2DPf8hNB19Y0Pe8tTvSrCuspFKa4Ic,12779
+sinabs/utils.py,sha256=1ctTxNT2ONYVK5d99VhZvXwxaOG4pD2lZ_PGRPPO6bQ,12114
+sinabs/validate_memory_speck.py,sha256=WKzB3o76sddUx9griloLQ6-ijDBPqFFXshdp9AjEiAM,5002
+sinabs/activation/__init__.py,sha256=cHXmIvV9fYZhqKVVTzD2F1a6KQklJPgTgDFjNzIEII8,311
+sinabs/activation/quantize.py,sha256=AzrIQbIlSPoiPgueC4XkRGNSeNoU5V9B7mtXbq0Kzk8,1166
+sinabs/activation/reset_mechanism.py,sha256=bGL3gMcG9xqD93HyGgKD6UlcOQ7MNGHllwxQfWVCb1k,1395
+sinabs/activation/spike_generation.py,sha256=vuU4f1H0TcTLspt_nAuUPLJQHuFt5em6ZNd9yXeja8M,3841
+sinabs/activation/surrogate_gradient_fn.py,sha256=iJE8IXmtYXYE6zCIFxx-MspfgtyUK-xJtiWBhLMq3q8,3814
+sinabs/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+sinabs/backend/dynapcnn/__init__.py,sha256=dx7N04c9_ibS4iLZIY6mLHv20EsOWEp5vZKvjAkxtwQ,305
+sinabs/backend/dynapcnn/chip_factory.py,sha256=XWwr0DoI3vB2GJy6iQd8sDPZlx6RvorT6OXGmWAAzNY,6805
+sinabs/backend/dynapcnn/config_builder.py,sha256=YacXNvCrr1m4zgexkyHq8Oe4cyOCaRSV6UQA-zNOSyk,4362
+sinabs/backend/dynapcnn/connectivity_specs.py,sha256=2Q_b0Gt_JaQCrfmzfebJy9EJWF6PLToLh_R1Y6ChRIM,1532
+sinabs/backend/dynapcnn/crop2d.py,sha256=-FKOQHdx8GjEXK64OlWZyc1GId4FFRptVnt80jLBlcs,1439
+sinabs/backend/dynapcnn/discretize.py,sha256=GyPfWjRg6I-kM2jo3ZXsBAk-3lCbPGZZamyD6Pz27yk,13319
+sinabs/backend/dynapcnn/dvs_layer.py,sha256=b9OryaOv5X5ZOxGOEZhabHZf3jZoykDuB295a2me3pw,8647
+sinabs/backend/dynapcnn/dynapcnn_layer.py,sha256=Pf-Qhl24LwKyu-7sJXDRYQ_3DN_7Z3MQyj3lNsGKTaE,8917
+sinabs/backend/dynapcnn/dynapcnn_layer_utils.py,sha256=9aPk9YuAgbfI_Xworfy-SbJDQSRVFksqaLU3ZaCmS74,13153
+sinabs/backend/dynapcnn/dynapcnn_network.py,sha256=klYI82qV1IqhDyD_OkOs5G3F-FysTtJJRgQbFEpDrfg,34721
+sinabs/backend/dynapcnn/dynapcnn_visualizer.py,sha256=MRewU6519dAtAMxf-JlFBrlynJTZeLiDfB0d85-mMFQ,24262
+sinabs/backend/dynapcnn/dynapcnnnetwork_module.py,sha256=aHLTAe59h_r0rZ0bHeSuIDG811MFP6_tOtyxiZIVVfA,14487
+sinabs/backend/dynapcnn/exceptions.py,sha256=MHvsM8a5c5ukHkH59OVYU0AeivVeNgdn9Tgqb07WOtU,3523
+sinabs/backend/dynapcnn/flipdims.py,sha256=I0I1nakrF0ngWBh-2SHHg7OkCOxotqukwHOQ45GWyCs,860
+sinabs/backend/dynapcnn/io.py,sha256=-XtP801uVragUlBf-6PjR5UHY6B0fcy1pUg0M6QlQKo,9999
+sinabs/backend/dynapcnn/mapping.py,sha256=sI0GKh2FkyciYFJuuCLCcitOzlEjfEEEbSG_OiJXICw,8683
+sinabs/backend/dynapcnn/nir_graph_extractor.py,sha256=1PbQzDokxW_0mzG_tdMSS1toHczW-2lnKGMUkdmCug8,37724
+sinabs/backend/dynapcnn/sinabs_edges_handler.py,sha256=pEfGUXwhQy7cnmofK5MCulSVFqMBDPRRoQVM5MTf3Qk,41085
+sinabs/backend/dynapcnn/specksim.py,sha256=UKh_lH_yHIZaYEONWsAOChrD-vBdSawBxRBeDHlSv84,17138
+sinabs/backend/dynapcnn/utils.py,sha256=QD5dKTgQmGLjP8fIz_vlXFpSem8Z-q-9zTebqd9xJzc,10036
+sinabs/backend/dynapcnn/weight_rescaling_methods.py,sha256=iftnMHZtAsPZ3wHDPPCR3VgTKjCsjNlZAIQwezWwyns,2051
+sinabs/backend/dynapcnn/chips/__init__.py,sha256=zJQ7f7bp_cF0US1pZ8ga4-3Bo32T0GB9gD2RN3uKlsM,130
+sinabs/backend/dynapcnn/chips/dynapcnn.py,sha256=oTfrBJ7ZxIaG2pNd59j3dk03QQvJWKjws6GImOX5W_0,15240
+sinabs/backend/dynapcnn/chips/speck2e.py,sha256=rq6RvS-FGE5aOtTXmvkKTmIJlwGxZz4vBFQ-nV3HLCo,879
+sinabs/backend/dynapcnn/chips/speck2f.py,sha256=bWGTFtUZzeZ7peZcgO1VQG_8YGyhiTQUKUE_X9jnC5E,877
+sinabs/layers/__init__.py,sha256=lRQtECdsYJzSWKppGcg_9oCHNRwjYprgmIDbJ21Kec0,584
+sinabs/layers/alif.py,sha256=20Tf0d9_dZaVNZl6n7qOUbL7EyICqYjmgv3UytVtf4Y,16196
+sinabs/layers/channel_shift.py,sha256=miS5BG4zbU0HtaWXaN_xBS7X3oX2ItBOjG_82fx7AYw,936
+sinabs/layers/crop2d.py,sha256=CV3kqsCsHi39aYvj4pz9cWT79JJ051HeAWrCTOet46M,1371
+sinabs/layers/exp_leak.py,sha256=HnKXZgDMZlRZfSHude8Nd1qLX2P_xV1C7KZlBmxviZo,3394
+sinabs/layers/iaf.py,sha256=S58p29fBE0wQdFEelZq2Qmb1m7rkLnYMyCpDVql2ASY,8001
+sinabs/layers/lif.py,sha256=V41sarXbFjGcd8RhX8NZIFHPr57-8zXssW7_kKJuicU,15293
+sinabs/layers/merge.py,sha256=oVtQXdtcXRivTlwDXTEbW1Ii-GTMkg3detp0-uCTcK0,985
+sinabs/layers/neuromorphic_relu.py,sha256=z8opQf38EJAWLpR2_k8d3MT8gxYA-s8aE8Jl9J7n4Lk,1545
+sinabs/layers/pool2d.py,sha256=NaV3KmjwV1lRTFLxo8BKt6hhRxAGwSFmSxmOPt6Ng_k,3553
+sinabs/layers/quantize.py,sha256=X9wKlA4nk8-_DS7WBiPHubHZQMb4OsSE0OkeFemxNCM,499
+sinabs/layers/reshape.py,sha256=mIbRoYsx3qAFK5MJtWL6wvof4KR8fKIpyIdbLv3ozPM,3347
+sinabs/layers/stateful_layer.py,sha256=5p5C6hySXor58lbUdQtmT9WfA5hrNcxzdriOH9Ct5f0,6685
+sinabs/layers/to_spike.py,sha256=ORkEGuHucWCqB3P1Ia8XJsPtpDAugCTSo7Bwr3xVpzE,3295
+sinabs/layers/functional/__init__.py,sha256=v0c7DHizKg8jfelmFYeMMg9vDafKvzoenakc4SPpj84,91
+sinabs/layers/functional/alif.py,sha256=ycJ7rlcBAd-lq5GCDZrcNPeV-7fztt3uy43XhBtTKHI,4599
+sinabs/layers/functional/lif.py,sha256=QRjiWDCBaJFk4J7RRMgktMaLCyN6xEXAKvC9Bu_PICU,4259
+sinabs-3.1.1.dist-info/licenses/AUTHORS,sha256=rSozYAiy4aFshSqHdw7bV-CyqtIyWhcPo26R5JR6-MY,1847
+sinabs-3.1.1.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+sinabs-3.1.1.dist-info/METADATA,sha256=N9GAqWDhMyzvI8UFqXW9IS1q5aKktZhm6rJleHlxDvg,3910
+sinabs-3.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sinabs-3.1.1.dist-info/pbr.json,sha256=Pzslm554HrYvSZWJBrXHy8I-yJ0JXOBa7BO2xjmMwAI,47
+sinabs-3.1.1.dist-info/top_level.txt,sha256=QOXGzf0ZeDjRnJ9OgAjkk6h5jrh66cwrwvtPJTyfDk8,7
+sinabs-3.1.1.dist-info/RECORD,,

{sinabs-3.0.4.dev25.dist-info → sinabs-3.1.1.dist-info}/licenses/AUTHORS

@@ -22,6 +22,7 @@ Vanessa Leite <vanessa.leite@synsense.ai>
 Vanessa Leite <vanessa@ini.uzh.ch>
 Vanessa Leite <vanessinhaleite.cp.ufma@gmail.com>
 Vanessa Leite <vrcleite@gmail.com>
+Willian Girao <williansoaresgirao@gmail.com>
 Willian-Girao <williansoaresgirao@gmail.com>
 Yalun Hu <yalun.hu@synsense.ai>
 Yalun_Hu <yalun.hu@synsense.ai>

sinabs-3.1.1.dist-info/pbr.json

@@ -0,0 +1 @@
+{"git_version": "cf8590b", "is_release": false}

sinabs-3.0.4.dev25.dist-info/RECORD

@@ -1,59 +0,0 @@
-sinabs/__init__.py,sha256=vvWzU_lrsSob2JpOdG7ok8Rm0FjR-v7ogYgK6zruAGk,458
-sinabs/cnnutils.py,sha256=MTVTmTnLYMiDQZozfgH7UhMCYQPpOto0vDa0kMjADiA,2406
-sinabs/conversion.py,sha256=k9pNqOtmA4JhKXIyGoFY6Fl8jyZp7DtlmpS4ym8pN0w,2023
-sinabs/from_torch.py,sha256=L_n7BRj7llKI-4Er1cPOZo6VVoInxehMk1PVlDiFIt8,4957
-sinabs/hooks.py,sha256=7jK44SxPcnQhWScvML9QIXyX5sfA_1E-lHpYjz2_4qc,16197
-sinabs/network.py,sha256=If6Qz2MDEpHPHD0bEStDyCif1EUw4ef3CXUQr4og9rA,9489
-sinabs/nir.py,sha256=r72RZ2WNuhnHvQ2MaSJ04J-Bes1mAdzoU9LKbJupZzE,8695
-sinabs/synopcounter.py,sha256=ZF7f9Au-j5wC3gPixWxj4yq8v8KdjDUMJWExyKi6Y5s,12759
-sinabs/utils.py,sha256=wNFwlf03SOYAEgdZiA1cxAf1XEnRXlycutEu2uhDBSQ,7696
-sinabs/validate_memory_speck.py,sha256=8uByUV9VNHncbYX4Wxq3qaepwfp-tH3c2MZeHRZSUeU,5134
-sinabs/activation/__init__.py,sha256=cHXmIvV9fYZhqKVVTzD2F1a6KQklJPgTgDFjNzIEII8,311
-sinabs/activation/quantize.py,sha256=AzrIQbIlSPoiPgueC4XkRGNSeNoU5V9B7mtXbq0Kzk8,1166
-sinabs/activation/reset_mechanism.py,sha256=aKtQFxB8WqzuSir0NocdkqTF_YD7E365QBj66g3wQvE,1419
-sinabs/activation/spike_generation.py,sha256=vuU4f1H0TcTLspt_nAuUPLJQHuFt5em6ZNd9yXeja8M,3841
-sinabs/activation/surrogate_gradient_fn.py,sha256=c07dIob-afODyBDcw_TtZ-n79lo-OL9NhwtA1aHJGL0,3834
-sinabs/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sinabs/backend/dynapcnn/__init__.py,sha256=m0Zr7WkmTHyGth0iQ7vsojnXd2Tb0yHE0hW6wfHkP_Y,179
-sinabs/backend/dynapcnn/chip_factory.py,sha256=Avy-CVu4-wxEMNcJmj0XVTfUEX7IGDbvVckMg5enVIo,6910
-sinabs/backend/dynapcnn/config_builder.py,sha256=oGbSwPxRd-qCT4cI6CBupbTl5Jh_B_3RhT3w-jaP8gQ,4795
-sinabs/backend/dynapcnn/crop2d.py,sha256=-FKOQHdx8GjEXK64OlWZyc1GId4FFRptVnt80jLBlcs,1439
-sinabs/backend/dynapcnn/discretize.py,sha256=5ZG4KHrIKB79ifGvt1gu6j8OlH0xc51cWQtyQHelJvg,13474
-sinabs/backend/dynapcnn/dvs_layer.py,sha256=Aauw7u7IJvtUkjOpYo1snqzVyFns6DZ5bmZGaj0Y7pA,9468
-sinabs/backend/dynapcnn/dynapcnn_layer.py,sha256=53u_7NqlNqJxTjrOeEOz4WABrYLtmclaN8sAwaSfr9Y,6702
-sinabs/backend/dynapcnn/dynapcnn_network.py,sha256=ZHNrf-KVwEf1gpUnH9CpHSUCVSAqxLAb6Ks3zbdZ6N0,20556
-sinabs/backend/dynapcnn/dynapcnn_visualizer.py,sha256=MRewU6519dAtAMxf-JlFBrlynJTZeLiDfB0d85-mMFQ,24262
-sinabs/backend/dynapcnn/exceptions.py,sha256=hEei4gOniq3ByYXkJovlAeaUfZ8Q9BWTHTb0DJ9pHeQ,485
-sinabs/backend/dynapcnn/flipdims.py,sha256=I0I1nakrF0ngWBh-2SHHg7OkCOxotqukwHOQ45GWyCs,860
-sinabs/backend/dynapcnn/io.py,sha256=1AN4CcixXM1PFZ6U3LeNGQ71ajSXaV3lTyq__j4sxns,9952
-sinabs/backend/dynapcnn/mapping.py,sha256=h63M9hhI6enZtQyq-may9hU7YcnGNCumiHalh8ohMno,6108
-sinabs/backend/dynapcnn/specksim.py,sha256=UKh_lH_yHIZaYEONWsAOChrD-vBdSawBxRBeDHlSv84,17138
-sinabs/backend/dynapcnn/utils.py,sha256=LYihrBIiPTDLUwsUikVOzWva4RwPc27LoHRCUDlDm-4,17934
-sinabs/backend/dynapcnn/chips/__init__.py,sha256=zJQ7f7bp_cF0US1pZ8ga4-3Bo32T0GB9gD2RN3uKlsM,130
-sinabs/backend/dynapcnn/chips/dynapcnn.py,sha256=hlAHijx7jdWkC_pS-3ju0QP3s0uKV4zC-19YdQJefPI,11473
-sinabs/backend/dynapcnn/chips/speck2e.py,sha256=NRk6MyUCTZh9Ohq1R7Bg1cYuwar1fAHqlya5mYJ6UGQ,936
-sinabs/backend/dynapcnn/chips/speck2f.py,sha256=YIjzkR74nyyK0Vcd9FmGqtSLDlIxxRBz5QwA_2F5hRI,928
-sinabs/layers/__init__.py,sha256=lRQtECdsYJzSWKppGcg_9oCHNRwjYprgmIDbJ21Kec0,584
-sinabs/layers/alif.py,sha256=gPHTH7hWsZ3CvbcLkcGBIuiDzft5jkPJsTOfj_lNClg,16294
-sinabs/layers/channel_shift.py,sha256=miS5BG4zbU0HtaWXaN_xBS7X3oX2ItBOjG_82fx7AYw,936
-sinabs/layers/crop2d.py,sha256=D8ClbqfwP12YNLoh7fhdpSHVH_vijxnsou1bEp8kgGY,1383
-sinabs/layers/exp_leak.py,sha256=eZVQQwnNkJ5TPuPEeXTfS0dKE8D4uK3cNCc-FDVexz0,3400
-sinabs/layers/iaf.py,sha256=6OKbyaCXy2_6SxujQ0YS2QNcTaKlS-mdNW5ghIx0TIQ,8065
-sinabs/layers/lif.py,sha256=TgbnMG6XLPKmM6zvX-3pciAlnbdjFfO5JFsLYOgQgU8,15324
-sinabs/layers/merge.py,sha256=oVtQXdtcXRivTlwDXTEbW1Ii-GTMkg3detp0-uCTcK0,985
-sinabs/layers/neuromorphic_relu.py,sha256=XKgq-WodkFt2Eizx2JMUwAaihS8gtoebsQ_IkK63mI8,1528
-sinabs/layers/pool2d.py,sha256=4JK71yge6IqMkbKuF425zP3GEfsvzE9XOsBCR_Js8bU,3562
-sinabs/layers/quantize.py,sha256=Qq1XOKwIKXGBxrMWYEC42NEZuDvhH1Rrz3d6l6ESQHs,505
-sinabs/layers/reshape.py,sha256=mIbRoYsx3qAFK5MJtWL6wvof4KR8fKIpyIdbLv3ozPM,3347
-sinabs/layers/stateful_layer.py,sha256=9aNLXuNfEqOTazNJRJ_-SMXxsTOs6-ZPEJNGkLJNMPw,6678
-sinabs/layers/to_spike.py,sha256=97ar-tiDZCgckBLdnKoHzm8PjTFwDXra0weOFgAf6_4,3313
-sinabs/layers/functional/__init__.py,sha256=v0c7DHizKg8jfelmFYeMMg9vDafKvzoenakc4SPpj84,91
-sinabs/layers/functional/alif.py,sha256=ycJ7rlcBAd-lq5GCDZrcNPeV-7fztt3uy43XhBtTKHI,4599
-sinabs/layers/functional/lif.py,sha256=QRjiWDCBaJFk4J7RRMgktMaLCyN6xEXAKvC9Bu_PICU,4259
-sinabs-3.0.4.dev25.dist-info/licenses/AUTHORS,sha256=jdt0oxfM_OW0_e5-ptxORAJ8U0uTzZjaB-F5iF2i50E,1802
-sinabs-3.0.4.dev25.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
-sinabs-3.0.4.dev25.dist-info/METADATA,sha256=lMBJ3gh6cNCYfTvWmV3LMMq72mw7pOM8nDo89vU3_gE,3893
-sinabs-3.0.4.dev25.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sinabs-3.0.4.dev25.dist-info/pbr.json,sha256=zYdy8PXt9BBw1ow-q9S5eIaTUBP1ICuh2q7SrAbkG40,47
-sinabs-3.0.4.dev25.dist-info/top_level.txt,sha256=QOXGzf0ZeDjRnJ9OgAjkk6h5jrh66cwrwvtPJTyfDk8,7
-sinabs-3.0.4.dev25.dist-info/RECORD,,

sinabs-3.0.4.dev25.dist-info/pbr.json

@@ -1 +0,0 @@
-{"git_version": "b38b049", "is_release": false}