Merge branch 'main' into libero_backend

Author: vloncar

.pre-commit-config.yaml

@@ -38,10 +38,10 @@ repos:
   rev: v3.19.1
   hooks:
   - id: pyupgrade
-    args: ["--py36-plus"]
+    args: ["--py310-plus"]
 
 - repo: https://github.com/pycqa/flake8
-  rev: 7.1.2
+  rev: 7.2.0
   hooks:
   - id: flake8
     exclude: docs/conf.py

docs/advanced/extension.rst

@@ -5,9 +5,9 @@ Extension API
 ``hls4ml`` natively supports a large number of neural network layers.
 But what if a desired layer is not supported?
 If it is standard enough and its implementation would benefit the community as a whole, we would welcome a contribution to add it to the standard set of supported layers.
-However, if it is a somewhat niche custom layer, there is another approach we can take to extend hls4ml through the *extension API*.
+However, if it is a somewhat niche custom layer, there is another approach we can take to extend hls4ml through the *extension API*. This feature is support for both keras and pytorch layers.
 
-This documentation will walk through a complete `complete end-to-end example <https://github.com/fastmachinelearning/hls4ml/blob/main/test/pytest/test_extensions.py>`_, which is part of our testing suite.
+Complete end-to-end examples are available for both `keras <https://github.com/fastmachinelearning/hls4ml/blob/main/test/pytest/test_extensions.py>`_ and `pytorch <https://github.com/fastmachinelearning/hls4ml/blob/main/test/pytest/test_extensions_pytorch.py>`_, which are part of our testing suite. The description here uses the keras example.
 To implement a custom layer in ``hls4ml`` with the extension API, the required components are:
 
 * Your custom layer class
@@ -18,9 +18,6 @@ To implement a custom layer in ``hls4ml`` with the extension API, the required c
 * Function config template
 * Registration of layer, source code, and templates
 
-.. note::
-    currently, then extension API supports keras models. Support for pytorch models is in development.
-
 Complete example
 ================
 

docs/intro/setup.rst

@@ -72,29 +72,55 @@ Here we give line-by-line instructions to demonstrate the general workflow.
 .. code-block:: python
 
    import hls4ml
+   import tensorflow as tf
+   from tensorflow.keras.layers import Dense
 
-   # Fetch a keras model from our example repository
-   # This will download our example model to your working directory and return an example configuration file
-   config = hls4ml.utils.fetch_example_model('KERAS_3layer.json')
+   # Construct a basic keras model
+   model = tf.keras.models.Sequential()
+   model.add(Dense(64, input_shape=(16,), name='Dense', kernel_initializer='lecun_uniform', kernel_regularizer=None))
+   model.add(Activation(activation='elu', name='Activation'))
+   model.add(Dense(32, name='Dense2', kernel_initializer='lecun_uniform', kernel_regularizer=None))
+   model.add(Activation(activation='elu', name='Activation2'))
 
-   # You can print it to see some default parameters
+   # This is where you would train the model in a real-world scenario
+
+   # Generate an hls configuration from the keras model
+   config = hls4ml.utils.config_from_keras_model(model)
+
+   # You can print the config to see some default parameters
    print(config)
 
-   # Convert it to a hls project
-   hls_model = hls4ml.converters.keras_to_hls(config)
+   # Convert the model to an hls project using the config
+   hls_model = hls4ml.converters.convert_from_keras_model(
+      model=model,
+      hls_config=config,
+      backend='Vitis'
+   )
+
+Once converted to an HLS project, you can connect the project into the Python runtime and use it to run predictions on a numpy array:
+
+.. code-block:: python
+
+   import numpy as np
+
+   # Compile the hls project and link it into the Python runtime
+   hls_model.compile()
+
+   # Generate random input data
+   X_input = np.random.rand(100, 16)
 
-   # Print full list of example model if you want to explore more
-   hls4ml.utils.fetch_example_list()
+   # Run the model on the input data
+   hls_prediction = hls_model.predict(X_input)
 
-After that, you can use :code:`Vivado HLS` to synthesize the model:
+After that, you can use :code:`Vitis HLS` to synthesize the model:
 
 .. code-block:: python
 
-   # Use Vivado HLS to synthesize the model
+   # Use Vitis HLS to synthesize the model
    # This might take several minutes
    hls_model.build()
 
-   # Print out the report if you want
+   # Optional: print out the report
    hls4ml.report.read_vivado_report('my-hls-test')
 
 Done! You've built your first project using ``hls4ml``! To learn more about our various API functionalities, check out our tutorials `here <https://github.com/fastmachinelearning/hls4ml-tutorial>`__.

hls4ml/backends/catapult/passes/bn_quant.py

@@ -96,7 +96,7 @@ def transform(self, model, node):
             bn_layer.get_weights('scale').data, bn_layer.get_weights('bias').data, node.get_attr('threshold', 0.5)
         )
         # Remove the BatchNormalization layer
-        model.remove_node(bn_layer, rewire=True)
+        model.remove_node(bn_layer)
         # Replace the old Activation layer with this one
         model.replace_node(node, bnbt_layer)
 

hls4ml/backends/fpga/passes/clone.py

@@ -61,8 +61,8 @@ def match(self, node):
 
         # Check if the output is used more than once
         output_map = node.get_output_use_map()
-        in_output = node.name in node.model.outputs
         for output in node.outputs:
+            in_output = output in node.model.outputs
             if len(output_map[output]) + in_output > 1:
                 # model output also need a stream
                 return True
@@ -72,10 +72,10 @@ def match(self, node):
     def transform(self, model, node):
 
         output_map = node.get_output_use_map()
-        in_output = node.name in node.model.outputs
 
         transformed = False
         for output in node.outputs:
+            in_output = output in node.model.outputs
             n_outputs = len(output_map[output]) + in_output
             if n_outputs == 1:
                 continue
@@ -90,8 +90,8 @@ def transform(self, model, node):
             init_stream_idx = 1
             if in_output:
                 # If the value is used as output, add one extra stream
-                idx = node.model.outputs.index(node.name)
-                node.model.outputs[idx] = node.name + '_cpy1'
+                idx = node.model.outputs.index(output)
+                node.model.outputs[idx] = output + '_cpy1'
                 init_stream_idx = 2
             for i, layer in enumerate(output_map[output], init_stream_idx):
                 idx = layer.inputs.index(output)
@@ -102,7 +102,7 @@ def transform(self, model, node):
                 'clone_' + node.name,
                 attrs,
                 [output],
-                [output + '_cpy' + str(i + 1) for i in range(n_outputs)],
+                [f'{output}_cpy{i + 1}' for i in range(n_outputs)],
             )
             for i in range(n_outputs):
                 key = output + '_cpy' + str(i + 1)

hls4ml/backends/fpga/passes/final_reshape.py

@@ -12,8 +12,7 @@ def match(self, node):
     def transform(self, model, node):
         if model.config.get_config_value('IOType') == 'io_parallel':
             print('WARNING: Final layer is a Reshape, which does not affect the output for io_parallel; removing it')
-            # remove, but don't rewire because it's the output layer
-            model.remove_node(node, rewire=False)
+            model.remove_node(node)
             return True
         elif model.config.get_config_value('IOType') == 'io_stream':
             print(

hls4ml/backends/fpga/passes/hgq_proxy_model.py

@@ -53,7 +53,7 @@ def match(self, node: Layer):
 
     def transform(self, model, node: FixedPointQuantizer):
         if node.fusible:
-            model.remove_node(node, rewire=True)
+            model.remove_node(node)
             return True
 
         if model.config.config['IOType'] != 'io_parallel':

hls4ml/backends/fpga/passes/remove_softmax.py

@@ -9,5 +9,5 @@ def match(self, node):
         return is_softmax and remove_softmax
 
     def transform(self, model, node):
-        model.remove_node(node, rewire=True)
+        model.remove_node(node)
         return True

hls4ml/backends/oneapi/oneapi_backend.py

@@ -10,6 +10,7 @@
 from hls4ml.model.layers import GRU, LSTM, Activation, Conv1D, Conv2D, Dense, Embedding, Layer, SimpleRNN, Softmax
 from hls4ml.model.optimizer import get_backend_passes, layer_optimizer
 from hls4ml.model.types import FixedPrecisionType, IntegerPrecisionType, NamedType
+from hls4ml.report import parse_oneapi_report
 from hls4ml.utils import attribute_descriptions as descriptions
 
 # from hls4ml.report import parse_oneapi_report
@@ -207,6 +208,8 @@ def build(self, model, build_type='fpga_emu', run=False):
             executable = builddir / f'{model.config.get_project_name()}.{build_type}'
             subprocess.run(f'{str(executable)}', shell=True, cwd=builddir, check=True)
 
+        return parse_oneapi_report(model.config.get_output_dir())
+
     @layer_optimizer(Layer)
     def init_base_layer(self, layer):
         reuse_factor = layer.model.config.get_reuse_factor(layer)

hls4ml/backends/oneapi/passes/bn_quant.py

@@ -149,7 +149,7 @@ def transform(self, model, node):
             bn_layer.get_weights('scale').data, bn_layer.get_weights('bias').data, node.get_attr('threshold', 0.5)
         )
         # Remove the BatchNormalization layer
-        model.remove_node(bn_layer, rewire=True)
+        model.remove_node(bn_layer)
         # Replace the old Activation layer with this one
         model.replace_node(node, bnbt_layer)