Merge branch 'fastmachinelearning:main' into main

.pre-commit-config.yaml

@@ -2,20 +2,26 @@ exclude: (^hls4ml\/templates\/(vivado|quartus)\/(ap_types|ac_types)\/|^test/pyte
 
 repos:
 - repo: https://github.com/psf/black
-  rev: 24.10.0
+  rev: 25.1.0
   hooks:
   - id: black
     language_version: python3
     args: ['--line-length=125',
            '--skip-string-normalization']
 
+- repo: https://github.com/tox-dev/pyproject-fmt
+  rev: v2.5.0
+  hooks:
+    - id: pyproject-fmt
+
 - repo: https://github.com/pre-commit/pre-commit-hooks
   rev: v5.0.0
   hooks:
   - id: check-added-large-files
   - id: check-case-conflict
   - id: check-merge-conflict
   - id: check-symlinks
+  - id: check-toml
   - id: check-yaml
   - id: debug-statements
   - id: end-of-file-fixer
@@ -24,22 +30,16 @@ repos:
   - id: trailing-whitespace
 
 - repo: https://github.com/PyCQA/isort
-  rev: 5.13.2
+  rev: 6.0.0
   hooks:
   - id: isort
-    args: ["--profile", "black", --line-length=125]
 
 - repo: https://github.com/asottile/pyupgrade
   rev: v3.19.1
   hooks:
   - id: pyupgrade
     args: ["--py36-plus"]
 
-- repo: https://github.com/asottile/setup-cfg-fmt
-  rev: v2.7.0
-  hooks:
-  - id: setup-cfg-fmt
-
 - repo: https://github.com/pycqa/flake8
   rev: 7.1.1
   hooks:

MANIFEST.in

@@ -1,7 +1,9 @@
-include LICENSE README.md CONTRIBUTING.md CITATION.cff pyproject.toml setup.py setup.cfg .clang-format
+include LICENSE README.md CONTRIBUTING.md CITATION.cff pyproject.toml .clang-format
 graft example-models
 graft test
 graft contrib
 recursive-include hls4ml/templates *
-global-exclude .git .gitmodules .gitlab-ci.yml
+recursive-include hls4ml *.py
+recursive-include hls4ml/contrib *
+global-exclude .git .gitmodules .gitlab-ci.yml *.pyc
 include hls4ml/backends/vivado_accelerator/supported_boards.json

hls4ml/__init__.py

@@ -1,33 +1,3 @@
-# Temporary workaround for QKeras installation requirement, will be removed after 1.0.0
-def maybe_install_qkeras():
-    import subprocess
-    import sys
-
-    QKERAS_PKG_NAME = 'QKeras'
-    # QKERAS_PKG_SOURCE = QKERAS_PKG_NAME
-    QKERAS_PKG_SOURCE = 'qkeras@git+https://github.com/fastmachinelearning/qkeras.git'
-
-    def pip_list():
-        p = subprocess.run([sys.executable, '-m', 'pip', 'list'], check=True, capture_output=True)
-        return p.stdout.decode()
-
-    def pip_install(package):
-        subprocess.check_call([sys.executable, '-m', 'pip', 'install', package])
-
-    all_pkgs = pip_list()
-    if QKERAS_PKG_NAME not in all_pkgs:
-        print('QKeras installation not found, installing one...')
-        pip_install(QKERAS_PKG_SOURCE)
-        print('QKeras installed.')
-
-
-try:
-    maybe_install_qkeras()
-except Exception:
-    print('Could not find QKeras installation, make sure you have QKeras installed.')
-
-# End of workaround
-
 from hls4ml import converters, report, utils  # noqa: F401, E402
 
 try:

hls4ml/backends/catapult/passes/conv_stream.py

@@ -6,7 +6,12 @@ class GenerateConvStreamingInstructions(OptimizerPass):
     '''Generates the instructions for streaming implementation of CNNs'''
 
     def match(self, node):
-        return isinstance(node, (Conv1D, SeparableConv1D, Conv2D, SeparableConv2D))
+        is_match = (
+            isinstance(node, (Conv1D, SeparableConv1D, Conv2D, SeparableConv2D))
+            and node.model.config.get_config_value('IOType').lower() == 'io_stream'
+            and node.get_attr('implementation').lower() == 'encoded'
+        )
+        return is_match
 
     def transform(self, model, node):
         node_class = node.__class__.__name__
@@ -18,35 +23,25 @@ def transform(self, model, node):
             raise Exception(f'Cannot generate instructions for node {node.name} ({node_class})')
 
     def _generate_1d_instructions(self, node):
-        if node.model.config.get_config_value('IOType') == 'io_stream':
-            min_w, instructions = node.model.config.backend.compute_conv1d_instructions(
-                node.get_input_variable().shape[0],
-                node.get_input_variable().shape[1],
-                node.get_attr('filt_width'),
-                node.get_attr('stride_width'),
-            )
-            instructions_str = ','.join(str(i) for i in instructions)
-            node.set_attr('min_width', min_w)
-            node.set_attr('instructions', instructions_str)
-        else:
-            # these are unused; just put dummy values
-            node.set_attr('min_width', node.get_attr('in_width'))
-            node.set_attr('instructions', '0')
+        min_w, instructions = node.model.config.backend.compute_conv1d_instructions(
+            node.get_input_variable().shape[0],
+            node.get_input_variable().shape[1],
+            node.get_attr('filt_width'),
+            node.get_attr('stride_width'),
+        )
+        instructions_str = ','.join(str(i) for i in instructions)
+        node.set_attr('min_width', min_w)
+        node.set_attr('instructions', instructions_str)
 
     def _generate_2d_instructions(self, node):
-        if node.model.config.get_config_value('IOType') == 'io_stream':
-            min_h, min_w, instructions = node.model.config.backend.compute_conv2d_instructions(
-                node.get_input_variable().shape[0],
-                node.get_input_variable().shape[1],
-                node.get_input_variable().shape[2],
-                node.get_attr('filt_height'),
-                node.get_attr('stride_height'),
-            )
-            instructions_str = ','.join(str(i) for i in instructions)
-            node.set_attr('min_height', min_h)
-            node.set_attr('min_width', min_w)
-            node.set_attr('instructions', instructions_str)
-        else:
-            node.set_attr('min_height', node.get_attr('in_height'))
-            node.set_attr('min_width', node.get_attr('in_width'))
-            node.set_attr('instructions', '0')
+        min_h, min_w, instructions = node.model.config.backend.compute_conv2d_instructions(
+            node.get_input_variable().shape[0],
+            node.get_input_variable().shape[1],
+            node.get_input_variable().shape[2],
+            node.get_attr('filt_height'),
+            node.get_attr('stride_height'),
+        )
+        instructions_str = ','.join(str(i) for i in instructions)
+        node.set_attr('min_height', min_h)
+        node.set_attr('min_width', min_w)
+        node.set_attr('instructions', instructions_str)

hls4ml/backends/catapult/passes/convolution_templates.py

@@ -135,6 +135,9 @@ def format(self, node):
         else:
             params['fill_fn'] = 'FillConv1DBuffer'
 
+        params['min_width'] = node.get_attr('min_width', node.get_attr('in_width'))
+        params['instructions'] = node.get_attr('instructions', '0')
+
         conv_config = self.template.format(**params)
 
         mult_params = self._default_config_params(node)
@@ -337,6 +340,10 @@ def format(self, node):
         else:
             params['fill_fn'] = 'FillConv2DBuffer'
 
+        params['min_height'] = node.get_attr('min_height', node.get_attr('in_height'))
+        params['min_width'] = node.get_attr('min_width', node.get_attr('in_width'))
+        params['instructions'] = node.get_attr('instructions', '0')
+
         conv_config = self.template.format(**params)
 
         mult_params = self._default_config_params(node)

hls4ml/backends/oneapi/passes/clone_templates.py

@@ -1,5 +1,4 @@
-""" The clone templates in the fpga backend are not enough for oneAPI, so this adds the missing parts
-"""
+"""The clone templates in the fpga backend are not enough for oneAPI, so this adds the missing parts"""
 
 from hls4ml.backends.fpga.passes.clone import Clone
 from hls4ml.backends.oneapi.oneapi_template import StreamFunctionCallTemplate, TaskSequenceTemplate

hls4ml/backends/vivado/passes/conv_stream.py

@@ -6,7 +6,12 @@ class GenerateConvStreamingInstructions(OptimizerPass):
     '''Generates the instructions for streaming implementation of CNNs'''
 
     def match(self, node):
-        return isinstance(node, (Conv1D, SeparableConv1D, Conv2D, SeparableConv2D))
+        is_match = (
+            isinstance(node, (Conv1D, SeparableConv1D, Conv2D, SeparableConv2D))
+            and node.model.config.get_config_value('IOType').lower() == 'io_stream'
+            and node.get_attr('implementation').lower() == 'encoded'
+        )
+        return is_match
 
     def transform(self, model, node):
         node_class = node.__class__.__name__
@@ -18,35 +23,25 @@ def transform(self, model, node):
             raise Exception(f'Cannot generate instructions for node {node.name} ({node_class})')
 
     def _generate_1d_instructions(self, node):
-        if node.model.config.get_config_value('IOType') == 'io_stream':
-            min_w, instructions = node.model.config.backend.compute_conv1d_instructions(
-                node.get_input_variable().shape[0],
-                node.get_input_variable().shape[1],
-                node.get_attr('filt_width'),
-                node.get_attr('stride_width'),
-            )
-            instructions_str = ','.join(str(i) for i in instructions)
-            node.set_attr('min_width', min_w)
-            node.set_attr('instructions', instructions_str)
-        else:
-            # these are unused; just put dummy values
-            node.set_attr('min_width', node.get_attr('in_width'))
-            node.set_attr('instructions', '0')
+        min_w, instructions = node.model.config.backend.compute_conv1d_instructions(
+            node.get_input_variable().shape[0],
+            node.get_input_variable().shape[1],
+            node.get_attr('filt_width'),
+            node.get_attr('stride_width'),
+        )
+        instructions_str = ','.join(str(i) for i in instructions)
+        node.set_attr('min_width', min_w)
+        node.set_attr('instructions', instructions_str)
 
     def _generate_2d_instructions(self, node):
-        if node.model.config.get_config_value('IOType') == 'io_stream':
-            min_h, min_w, instructions = node.model.config.backend.compute_conv2d_instructions(
-                node.get_input_variable().shape[0],
-                node.get_input_variable().shape[1],
-                node.get_input_variable().shape[2],
-                node.get_attr('filt_height'),
-                node.get_attr('stride_height'),
-            )
-            instructions_str = ','.join(str(i) for i in instructions)
-            node.set_attr('min_height', min_h)
-            node.set_attr('min_width', min_w)
-            node.set_attr('instructions', instructions_str)
-        else:
-            node.set_attr('min_height', node.get_attr('in_height'))
-            node.set_attr('min_width', node.get_attr('in_width'))
-            node.set_attr('instructions', '0')
+        min_h, min_w, instructions = node.model.config.backend.compute_conv2d_instructions(
+            node.get_input_variable().shape[0],
+            node.get_input_variable().shape[1],
+            node.get_input_variable().shape[2],
+            node.get_attr('filt_height'),
+            node.get_attr('stride_height'),
+        )
+        instructions_str = ','.join(str(i) for i in instructions)
+        node.set_attr('min_height', min_h)
+        node.set_attr('min_width', min_w)
+        node.set_attr('instructions', instructions_str)

hls4ml/backends/vivado/passes/convolution_templates.py

@@ -108,6 +108,9 @@ def format(self, node):
             else:
                 params['conv_fn'] = 'Conv1DResource'
 
+        params['min_width'] = node.get_attr('min_width', node.get_attr('in_width'))
+        params['instructions'] = node.get_attr('instructions', '0')
+
         conv_config = self.template.format(**params)
 
         mult_params = self._default_config_params(node)
@@ -239,6 +242,10 @@ def format(self, node):
         else:
             params['fill_fn'] = 'FillConv2DBuffer'
 
+        params['min_height'] = node.get_attr('min_height', node.get_attr('in_height'))
+        params['min_width'] = node.get_attr('min_width', node.get_attr('in_width'))
+        params['instructions'] = node.get_attr('instructions', '0')
+
         conv_config = self.template.format(**params)
 
         mult_params = self._default_config_params(node)

hls4ml/backends/vivado/passes/recurrent_templates.py

@@ -4,7 +4,7 @@
 
 # recurrent multiplication template
 
-recr_mult_config_template = """struct config{index} : nnet::dense_config {{
+recr_mult_config_template_1 = """struct config{index} : nnet::dense_config {{
     static const unsigned n_in = {n_in};
     static const unsigned n_out = {n_out};
     static const unsigned strategy = nnet::{strategy};
@@ -22,6 +22,24 @@
     using product = nnet::product::{product_type}<x_T, y_T>;
 }};\n"""
 
+recr_mult_config_template_2 = """struct config{index} : nnet::dense_config {{
+    static const unsigned n_in = {n_in};
+    static const unsigned n_out = {n_out};
+    static const unsigned strategy = nnet::{strategy};
+    static const unsigned reuse_factor = {reuse};
+    static const unsigned n_zeros = {nzeros};
+    static const unsigned n_nonzeros = {nonzeros};
+    static const unsigned multiplier_limit = DIV_ROUNDUP(n_in * n_out, reuse_factor) - n_zeros / reuse_factor;
+    static const bool store_weights_in_bram = false;
+    typedef {accum_t.name} accum_t;
+    typedef {recurrent_bias_t.name} bias_t;
+    typedef {recurrent_weight_t.name} weight_t;
+    template<class data_T, class res_T, class CONFIG_T>
+    using kernel = nnet::{dense_function}<data_T, res_T, CONFIG_T>;
+    template<class x_T, class y_T>
+    using product = nnet::product::{product_type}<x_T, y_T>;
+}};\n"""
+
 # activation templates
 
 activ_config_template = """struct {type}_config{index} : nnet::activ_config {{
@@ -45,7 +63,9 @@
 recr_config_template = """struct config{index} : nnet::{recr_type}_config {{
     typedef {accum_t.name} accum_t;
     typedef {weight_t.name} weight_t;  // Matrix
+    typedef {recurrent_weight_t.name} recurrent_weight_t;  // Matrix
     typedef {bias_t.name} bias_t;  // Vector
+    typedef {recurrent_bias_t.name} recurrent_bias_t;  // Vector
     typedef {config_mult_t1} mult_config1;
     typedef {config_mult_t2} mult_config2;
     typedef {recr_act_t} ACT_CONFIG_{RECR_TYPE};
@@ -77,8 +97,8 @@ def __init__(self):
         self.template = recr_config_template
         self.act_template = activ_config_template
         self.recr_act_template = recr_activ_config_template
-        self.mult1_template = recr_mult_config_template
-        self.mult2_template = recr_mult_config_template
+        self.mult1_template = recr_mult_config_template_1
+        self.mult2_template = recr_mult_config_template_2
 
     def format(self, node):
         params = self._default_config_params(node)

hls4ml/cli/__main__.py

@@ -0,0 +1,3 @@
+from . import main
+
+main()

contrib/kl_layer/kl_layer.py → hls4ml/contrib/kl_layer/kl_layer.py

@@ -1,10 +1,10 @@
 """
-    Usage example for a custom KL loss layer
-    Takes as an input two arrays: z_mean and z_log_var
-    and computes KL "distance" between normal distribution
-    and Gaussian with mu=z_mean and sigma=z_log_var
+Usage example for a custom KL loss layer
+Takes as an input two arrays: z_mean and z_log_var
+and computes KL "distance" between normal distribution
+and Gaussian with mu=z_mean and sigma=z_log_var
 
-    The HLS part is in contrib/kl_layer/kl_layer.h
+The HLS part is in contrib/kl_layer/kl_layer.h
 """
 
 from pathlib import Path