Netx (#30)

* Updated readme and tutuorial links.

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* PilotNet verified in Netx

* PiloteNet verified in NetX. Minor liniting fixes.

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Changes to accompany io read and reset api changes.

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Pilotnet SDNN tested

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* pilotnet sdnn tutorial

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* PilotNet SDNN notebook

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Removed dataset gt logging

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* fixed sdnn notebook plot label

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Integrated virtualport api to swicth from conv to dense layer

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* dense graded input support added. Cleaned up sdnn notebook

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Refport insconsistency in snn notebook

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Linting fixes. Updated build script

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Changed dates in copyright header

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Readme Updates and review comments fixes

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Fixed linting issue

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Cleaned up snn notebook. Fixed issue with lambda on Windows.

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* Fixed test_hdf5 tests to reflect in_layer transform changes

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

* final tid bits

Signed-off-by: bamsumit <bam_sumit@hotmail.com>

Co-authored-by: Marcus G K Williams <marcus.williams@intel.com>

README.md

@@ -16,9 +16,7 @@ The library presently consists of
 
 1. `lava.lib.dl.slayer` for natively training Deep Event-Based Networks.
 2. `lava.lib.dl.bootstrap` for training rate coded SNNs.
-
-Coming soon to the library
-1. `lava.lib.dl.netx` for training and deployment of event-based deep neural networks on traditional as well as neuromorphic backends.
+3. `lava.lib.dl.netx` for training and deployment of event-based deep neural networks on traditional as well as neuromorphic backends.
 
 More tools will be added in the future.
 
@@ -112,15 +110,20 @@ $ pip install lava-nc-0.1.0.tar.gz
 
 ## Getting Started
 
-**End to end tutorials**
+**End to end training tutorials**
 * [Oxford spike train regression](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/slayer/oxford/train.ipynb)
 * [MNIST digit classification](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/bootstrap/mnist/train.ipynb)
 * [NMNIST digit classification](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/slayer/nmnist/train.ipynb)
 * [PilotNet steering angle prediction](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/slayer/pilotnet/train.ipynb)
 
-**Deep dive tutorials**
+**Deep dive training tutorials**
 * [Dynamics and Neurons](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/slayer/neuron_dynamics/dynamics.ipynb)
 
+**Inference tutorials**
+* [Oxford Inference](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/netx/oxford/run.ipynb)
+* [PilotNet SNN Inference](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/netx/pilotnet_snn/run.ipynb)
+* [PilotNet SDNN Inference](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/netx/pilotnet_sdnn/run.ipynb)
+
 ## __`lava.lib.dl.slayer`__ 
 
 `lava.lib.dl.slayer` is an enhanced version of [SLAYER](https://github.com/bamsumit/slayerPytorch). Most noteworthy enhancements are: support for _recurrent network structures_, a wider variety of _neuron models_ and _synaptic connections_ (a complete list of features is [here](https://github.com/lava-nc/lava-dl/blob/main/src/lava/lib/dl/slayer/README.md)). This version of SLAYER is built on top of the [PyTorch](https://pytorch.org/) deep learning framework, similar to its predecessor. For smooth integration with Lava, `lava.lib.dl.slayer` supports exporting trained models using the platform independent __hdf5 network exchange__ format. 
@@ -263,27 +266,30 @@ __Load the trained network__
 # Import the model as a Lava Process
 net = hdf5.Network(net_config='network.net')
 ```
-__Attach Processes for Input Injection and Output Readout__
+__Attach Processes for Input-Output interaction__
 ```python
-from lava.proc.io import InputLoader, BiasWriter, OutputReader
+from lava.proc import io
 
 # Instantiate the processes
-input_loader = InputLoader(dataset=testing_set)
-bias_writer = BiasWriter(shape=input_shape)
-output = OutputReader()
+dataloader = io.dataloader.SpikeDataloader(dataset=test_set)
+output_logger = io.sink.RingBuffer(shape=net.out_layer.shape, buffer=num_steps)
+gt_logger = io.sink.RingBuffer(shape=(1,), buffer=num_steps)
 
 # Connect the input to the network:
-input_loader.data_out.connect(bias_writer.bias_in)
-bias_writer.bias_out.connect(net.in_layer.bias)
+dataloader.ground_truth.connect(gt_logger.a_in)
+dataloader.s_out.connect(net.in_layer.neuron.a_in)
 
 # Connect network-output to the output process
-net.out_layer.neuron.s_out.connect(output.net_output_in)
+net.out_layer.out.connect(output_logger.a_in)
 ```
 __Run the network__
 ```python
 from lava.magma import run_configs as rcfg
 from lava.magma import run_conditions as rcnd
 
 net.run(condition=rcnd.RunSteps(total_run_time), run_cfg=rcfg.Loihi1SimCfg())
+output = output_logger.data.get()
+gts = gt_logger.data.get()
+net.stop()
 ```
 

build.py

@@ -67,6 +67,7 @@ def set_properties_unit(project):
     project.set_property("dir_source_unittest_python", "tests/lava")
     project.set_property("dir_source_main_scripts", "scripts")
     project.set_property("dir_docs", "docs")
+    project.build_depends_on("lava", url="git+https://github.com/lava-nc/lava.git")
 
     project.set_property("sphinx_config_path", "docs")
     project.set_property("sphinx_source_dir", "docs")
@@ -82,7 +83,7 @@ def set_properties_unit(project):
     project.plugin_depends_on("sphinx_tabs")
 
     project.set_property("verbose", True)
-    
+
     project.set_property("coverage_threshold_warn", 0)
     project.set_property("coverage_break_build", False)
 

requirements.txt

@@ -5,3 +5,4 @@ scipy
 matplotlib
 ninja
 h5py >= 3.1.0
+lava-nc@git+https://github.com/lava-nc/lava.git

src/lava/lib/dl/bootstrap/__init__.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021 Intel Corporation
+# Copyright (C) 2022 Intel Corporation
 # SPDX-License-Identifier:  BSD-3-Clause
 
 

src/lava/lib/dl/bootstrap/ann_sampler.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021 Intel Corporation
+# Copyright (C) 2022 Intel Corporation
 # SPDX-License-Identifier:  BSD-3-Clause
 
 """ANN sampler module."""

src/lava/lib/dl/bootstrap/block/__init__.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021 Intel Corporation
+# Copyright (C) 2022 Intel Corporation
 # SPDX-License-Identifier:  BSD-3-Clause
 
 from . import base, cuba

src/lava/lib/dl/bootstrap/block/base.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021 Intel Corporation
+# Copyright (C) 2022 Intel Corporation
 # SPDX-License-Identifier:  BSD-3-Clause
 
 """Abstract bootstrap layer blocks."""

src/lava/lib/dl/bootstrap/block/cuba.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021 Intel Corporation
+# Copyright (C) 2022 Intel Corporation
 # SPDX-License-Identifier:  BSD-3-Clause
 
 """Bootstrap CUBA layer blocks."""

src/lava/lib/dl/bootstrap/routine.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2021 Intel Corporation
+# Copyright (C) 2022 Intel Corporation
 # SPDX-License-Identifier:  BSD-3-Clause
 
 """ANN-SNN mode switching routine helper."""

src/lava/lib/dl/netx/__init__.py

@@ -0,0 +1,7 @@
+# Copyright (C) 2022 Intel Corporation
+# SPDX-License-Identifier:  BSD-3-Clause
+
+from . import hdf5
+from . import blocks
+
+__all__ = ['hdf5', 'blocks']

src/lava/lib/dl/netx/blocks/models.py

@@ -0,0 +1,51 @@
+# Copyright (C) 2022 Intel Corporation
+# SPDX-License-Identifier:  BSD-3-Clause
+
+import numpy as np
+
+from lava.magma.core.process.process import AbstractProcess
+from lava.magma.core.model.py.ports import PyInPort, PyOutPort
+from lava.magma.core.model.py.type import LavaPyType
+from lava.magma.core.decorator import implements, requires, tag
+from lava.magma.core.model.sub.model import AbstractSubProcessModel
+from lava.magma.core.sync.protocols.loihi_protocol import LoihiProtocol
+from lava.magma.core.resources import CPU
+
+from lava.lib.dl.netx.blocks.process import Input, Dense, Conv
+
+
+@requires(CPU)
+@tag('fixed_pt')
+class AbstractPyBlockModel(AbstractSubProcessModel):
+    """Abstract Block model. A block typically encapsulates at least a
+    synapse and a neuron in a layer. It could also include recurrent
+    connection as well as residual connection. A minimal example of a
+    block is a feedforward layer."""
+    def __init__(self, proc: AbstractProcess) -> None:
+        if proc.has_graded_input:
+            self.inp: PyInPort = LavaPyType(np.ndarray, np.int32, precision=32)
+        else:
+            self.inp: PyInPort = LavaPyType(np.ndarray, np.int8, precision=1)
+
+        if proc.has_graded_output:
+            self.out: PyOutPort = LavaPyType(np.ndarray, np.int32, precision=32)
+        else:
+            self.out: PyOutPort = LavaPyType(np.ndarray, np.int8, precision=1)
+
+
+@implements(proc=Input, protocol=LoihiProtocol)
+class PyInputModel(AbstractPyBlockModel):
+    def __init__(self, proc: AbstractProcess) -> None:
+        super().__init__(proc)
+
+
+@implements(proc=Dense, protocol=LoihiProtocol)
+class PyDenseModel(AbstractPyBlockModel):
+    def __init__(self, proc: AbstractProcess) -> None:
+        super().__init__(proc)
+
+
+@implements(proc=Conv, protocol=LoihiProtocol)
+class PyConvModel(AbstractPyBlockModel):
+    def __init__(self, proc: AbstractProcess) -> None:
+        super().__init__(proc)