triggerflow 0.1.4__py3-none-any.whl → 0.2.4__py3-none-any.whl

triggerflow/templates/model-gt.cpp

@@ -0,0 +1,104 @@
+#include "{{MODEL_NAME}}_project.h"
+#include "data_types.h"
+
+namespace {{MODEL_NAME}} {
+
+typedef {{OFFSET_TYPE}} offset_t;
+typedef {{SHIFT_TYPE}}  shift_t;
+
+static const offset_t NN_OFFSETS[{{N_INPUTS}}] = { {{NN_OFFSETS}} };
+static const shift_t  NN_SHIFTS[{{N_INPUTS}}]  = { {{NN_SHIFTS}} };
+
+static void scaleNNInputs(
+    input_t unscaled[{{N_INPUTS}}],
+    input_t scaled[{{N_INPUTS}}]
+) {
+    #pragma HLS pipeline
+    for (int i = 0; i < {{N_INPUTS}}; i++) {
+        #pragma HLS unroll
+        input_t tmp0 = unscaled[i] - NN_OFFSETS[i];
+        input_t tmp1 = tmp0 >> NN_SHIFTS[i];
+        scaled[i] = tmp1;
+    }
+}
+
+void {{MODEL_NAME}}_GT(
+    Muon      muons[{{MUON_SIZE}}],
+    Jet       jets[{{JET_SIZE}}],
+    EGamma    egammas[{{EGAMMA_SIZE}}],
+    Tau       taus[{{TAU_SIZE}}],
+    ET        et,
+    HT        ht,
+    ETMiss    etmiss,
+    HTMiss    htmiss,
+    ETHFMiss  ethfmiss,
+    HTHFMiss  hthfmiss,
+    {{OUTPUT_TYPE}} {{OUTPUT_LAYER}}
+) {
+    #pragma HLS aggregate variable=muons compact=bit
+    #pragma HLS aggregate variable=jets compact=bit
+    #pragma HLS aggregate variable=egammas compact=bit
+    #pragma HLS aggregate variable=taus compact=bit
+    #pragma HLS aggregate variable=et compact=bit
+    #pragma HLS aggregate variable=ht compact=bit
+    #pragma HLS aggregate variable=etmiss compact=bit
+    #pragma HLS aggregate variable=htmiss compact=bit
+    #pragma HLS aggregate variable=ethfmiss compact=bit
+    #pragma HLS aggregate variable=hthfmiss compact=bit
+
+    #pragma HLS array_partition variable=muons complete
+    #pragma HLS array_partition variable=jets complete
+    #pragma HLS array_partition variable=egammas complete
+    #pragma HLS array_partition variable=taus complete
+
+    #pragma HLS pipeline II=1
+    #pragma HLS latency min=2 max=2
+    #pragma HLS inline recursive
+
+    input_t input_unscaled[{{N_INPUTS}}];
+    input_t input_scaled[{{N_INPUTS}}];
+    int idx = 0;
+
+    // Muons
+    for (int i = 0; i < {{MUON_SIZE}}; i++) {
+        #pragma HLS unroll
+        {% for f in MUON_FEATURES %}
+        input_unscaled[idx++] = muons[i].{{f}};
+        {% endfor %}
+    }
+
+    // Jets
+    for (int i = 0; i < {{JET_SIZE}}; i++) {
+        #pragma HLS unroll
+        {% for f in JET_FEATURES %}
+        input_unscaled[idx++] = jets[i].{{f}};
+        {% endfor %}
+    }
+
+    // EGammas
+    for (int i = 0; i < {{EGAMMA_SIZE}}; i++) {
+        #pragma HLS unroll
+        {% for f in EGAMMA_FEATURES %}
+        input_unscaled[idx++] = egammas[i].{{f}};
+        {% endfor %}
+    }
+
+    // Taus
+    for (int i = 0; i < {{TAU_SIZE}}; i++) {
+        #pragma HLS unroll
+        {% for f in TAU_FEATURES %}
+        input_unscaled[idx++] = taus[i].{{f}};
+        {% endfor %}
+    }
+
+    // Scalars / global objects
+    {% for f in GLOBAL_FEATURES %}
+    input_unscaled[idx++] = {{f}};
+    {% endfor %}
+
+    scaleNNInputs(input_unscaled, input_scaled);
+
+    {{MODEL_NAME}}_project(input_scaled, {{OUT}});
+}
+
+} // namespace {{MODEL_NAME}}

triggerflow/templates/model_template.cpp

@@ -1,4 +1,4 @@
-#include "NN/{{MODEL_NAME}}.h"
+#include "NN/{{MODEL_NAME}}_project.h"
 #include "emulator.h"
 #include "NN/nnet_utils/nnet_common.h"
 #include <any>
@@ -13,40 +13,41 @@ using namespace hls4ml_{{MODEL_NAME}};
 class {{MODEL_NAME}}_emulator : public hls4mlEmulator::Model {
 
 private:
-    unscaled_t _unscaled_input[N_INPUT_1_1];
-    input_t _scaled_input[N_INPUT_1_1];
-    result_t _result[{{N_OUTPUTS}}];
+    typedef {{UNSCALED_TYPE}} unscaled_t;
+    static const int N_INPUT_SIZE = {{N_INPUTS}};
 
-    virtual void _scaleNNInputs(unscaled_t unscaled[N_INPUT_1_1], input_t scaled[N_INPUT_1_1])
+    unscaled_t _unscaled_input[N_INPUT_SIZE];
+    {{MODEL_NAME}}::input_t _scaled_input;
+    {{MODEL_NAME}}::result_t _result;
+
+    // Scale the raw input array to the model input type
+    virtual void _scaleNNInputs(unscaled_t unscaled[N_INPUT_SIZE], {{MODEL_NAME}}::input_t &scaled)
     {
-        for (int i = 0; i < N_INPUT_1_1; i++)
+        for (int i = 0; i < N_INPUT_SIZE; i++)
         {
             unscaled_t tmp0 = unscaled[i] - hls4ml_{{MODEL_NAME}}::ad_offsets[i];
-            input_t tmp1 = tmp0 >> hls4ml_{{MODEL_NAME}}::ad_shift[i];
+            {{UNSCALED_TYPE}} tmp1 = tmp0 >> hls4ml_{{MODEL_NAME}}::ad_shift[i];
             scaled[i] = tmp1;
         }
     }
 
-public: 
+public:
     virtual void prepare_input(std::any input) {
         unscaled_t *unscaled_input_p = std::any_cast<unscaled_t*>(input);
-        
-        for (int i = 0; i < N_INPUT_1_1; i++) {
-            _unscaled_input[i] = std::any_cast<unscaled_t>(unscaled_input_p[i]);
+        for (int i = 0; i < N_INPUT_SIZE; i++) {
+            _unscaled_input[i] = unscaled_input_p[i];
         }
-
         _scaleNNInputs(_unscaled_input, _scaled_input);
     }
 
     virtual void predict() {
-        {{MODEL_NAME}}(_scaled_input, _result);
+        // Call the io_parallel model function; pass pointers
+        {{MODEL_NAME}}::{{MODEL_NAME}}_project(&_scaled_input, &_result);
     }
-  
+
     virtual void read_result(std::any result) {
-        result_t *result_p = std::any_cast<result_t*>(result);
-        for (int i = 0; i < {{N_OUTPUTS}}; i++) {
-            result_p[i] = _result[i];
-        }
+        {{MODEL_NAME}}::result_t *result_p = std::any_cast<{{MODEL_NAME}}::result_t*>(result);
+        *result_p = _result;
     }
 };
 

triggerflow/templates/scales.h

@@ -1,7 +1,7 @@
 #ifndef __ADT_SCALES_H
 #define __ADT_SCALES_H
 
-#include "NN/{{MODEL_NAME}}.h"
+#include "NN/{{MODEL_NAME}}_project.h"
 
 namespace hls4ml_{{MODEL_NAME}} {
 

triggerflow-0.2.4.dist-info/METADATA

@@ -0,0 +1,192 @@
+Metadata-Version: 2.4
+Name: triggerflow
+Version: 0.2.4
+Summary: Utilities for ML models targeting hardware triggers
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: cookiecutter>=2.3
+Requires-Dist: PyYAML>=6
+Requires-Dist: Jinja2>=3
+Requires-Dist: mlflow>=2.0
+Requires-Dist: kedro==1.0.0
+Provides-Extra: dev
+Requires-Dist: pytest-cov~=3.0; extra == "dev"
+Requires-Dist: pytest-mock<2.0,>=1.7.1; extra == "dev"
+Requires-Dist: pytest~=7.2; extra == "dev"
+Requires-Dist: ruff~=0.1.8; extra == "dev"
+Provides-Extra: extended
+Requires-Dist: coffea; extra == "extended"
+Requires-Dist: dask; extra == "extended"
+Requires-Dist: pyarrow; extra == "extended"
+Requires-Dist: pandas==2.0.3; extra == "extended"
+Requires-Dist: uproot4==4.0.0; extra == "extended"
+Requires-Dist: pyarrow==17.0.0; extra == "extended"
+Requires-Dist: hist==2.7.3; extra == "extended"
+Requires-Dist: mlflow==2.21.0; extra == "extended"
+Requires-Dist: tensorflow==2.13.0; extra == "extended"
+Requires-Dist: QKeras==0.9.0; extra == "extended"
+Requires-Dist: keras==2.13.1; extra == "extended"
+Requires-Dist: numpy; extra == "extended"
+Requires-Dist: pyparsing; extra == "extended"
+Requires-Dist: PyYAML; extra == "extended"
+Requires-Dist: matplotlib; extra == "extended"
+Requires-Dist: mplhep; extra == "extended"
+Requires-Dist: h5py; extra == "extended"
+Requires-Dist: xxhash; extra == "extended"
+Requires-Dist: shap; extra == "extended"
+Requires-Dist: awkward-pandas; extra == "extended"
+Requires-Dist: qonnx==0.4.0; extra == "extended"
+Requires-Dist: tf_keras; extra == "extended"
+Requires-Dist: tf2onnx; extra == "extended"
+Requires-Dist: hls4ml; extra == "extended"
+Requires-Dist: conifer; extra == "extended"
+
+# Machine Learning for Hardware Triggers
+
+`triggerflow` provides a set of utilities for Machine Learning models targeting FPGA deployment. 
+The `TriggerModel` class consolidates several Machine Learning frontends and compiler backends to construct a "trigger model". MLflow utilities are for logging, versioning, and loading of trigger models.
+
+## Installation
+
+```bash
+pip install triggerflow
+```
+
+## Usage
+
+```python
+
+from triggerflow.core import TriggerModel
+
+
+scales = {'offsets': np.array([18, 0, 72, 7, 0, 73, 4, 0, 73, 4, 0, 72, 3, 0, 72, 6, -0, 286, 3, -2, 285, 3, -2, 282, 3, -2, 286, 29, 0, 72, 22, 0, 72, 18, 0, 72, 14, 0, 72, 11, 0, 72, 10, 0, 72, 10, 0, 73, 9, 0], dtype='int'),
+'shifts': np.array([3, 0, 6, 2, 5, 6, 0, 5, 6, 0, 5, 6, -1, 5, 6, 2, 7, 8, 0, 7, 8, 0, 7, 8, 0, 7, 8, 4, 6, 6, 3, 6, 6, 3, 6, 6, 3, 6, 6, 3, 6, 6, 3, 6, 6, 3, 6, 6, 3, 6], dtype='int')}
+
+
+trigger_model = TriggerModel(
+    config="triggermodel_config.yaml",
+    native_model=model, #Native XGboost/Keras model
+    scales=scales
+)
+
+trigger_model() #Vivado requird on $PATH for Firmware build.
+
+# then:
+output_software = trigger_model.software_predict(input_data)
+output_firmware = trigger_model.firmware_predict(input_data)
+output_qonnx = trigger_model.qonnx_predict(input_data)
+
+# save and load trigger models:
+trigger_model.save("triggerflow.tar.xz")
+
+# in a separate session:
+from triggerflow.core import TriggerModel
+triggerflow = TriggerModel.load("triggerflow.tar.xz")
+```
+
+## The Config file:
+
+Use this `.yaml` template and change as needed. 
+
+```yaml
+compiler:
+  name: "AXO"
+  ml_backend: "keras"
+  compiler: "hls4ml"
+  fpga_part: "xc7vx690t-ffg1927-2"
+  clock_period: 25
+  n_outputs: 1
+  project_name: "AXO_project"
+  namespace: "AXO"
+  io_type: "io_parallel"
+  backend: "Vitis"
+  write_weights_txt: false
+
+subsystem:
+  name: "uGT"
+  n_inputs: 50
+  offset_type: "ap_fixed<10,10>"
+  shift_type: "ap_fixed<10,10>"
+
+  objects:
+    muons:
+      size: 4
+      features: [pt, eta_extrapolated, phi_extrapolated]
+
+    jets:
+      size: 4
+      features: [et, eta, phi]
+
+    egammas:
+      size: 4
+      features: [et, eta, phi]
+
+    taus:
+      size: 4
+      features: [et, eta, phi]
+
+  global_features:
+    #- et.et
+    #- ht.et
+    - etmiss.et
+    - etmiss.phi
+    #- htmiss.et
+    #- htmiss.phi
+    #- ethfmiss.et
+    #- ethfmiss.phi
+    #- hthfmiss.et
+    #- hthfmiss.phi
+
+  muon_size: 4
+  jet_size: 4
+  egamma_size: 4
+  tau_size: 4
+```
+
+## Logging with MLflow
+
+```python
+# logging with MLFlow:
+import mlflow
+from triggerflow.mlflow_wrapper import log_model
+
+mlflow.set_tracking_uri("https://ngt.cern.ch/models")
+experiment_id = mlflow.create_experiment("example-experiment")
+
+with mlflow.start_run(run_name="trial-v1", experiment_id=experiment_id):
+    log_model(triggerflow, registered_model_name="TriggerModel")
+```
+
+### Note: This package doesn't install dependencies so it won't disrupt specific training environments or custom compilers. For a reference environment, see `environment.yml`.
+
+
+# Creating a kedro pipeline
+
+This repository also comes with a default pipeline for trigger models based on kedro.
+One can create a new pipeline via:
+
+NOTE: no "-" and upper cases!
+
+```bash
+# Create a conda environment & activate it
+conda create -n triggerflow python=3.11
+conda activate triggerflow
+
+# install triggerflow
+pip install triggerflow
+
+# Create a pipeline
+triggerflow new demo_pipeline
+
+# NOTE: since we dont install dependency one has to create a
+# conda env based on the environment.yml file of the pipeline
+# this file can be changed to the needs of the indiviual project
+cd demo_pipeline
+conda env update -n triggerflow --file environment.yml
+
+# Run Kedro
+kedro run
+```

triggerflow-0.2.4.dist-info/RECORD

@@ -0,0 +1,102 @@
+trigger_dataset/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+trigger_dataset/core.py,sha256=ZX96U6rWxxfCatDQbst6IRZvtlyDj1_2JA7stPydGTQ,2645
+trigger_loader/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+trigger_loader/cluster_manager.py,sha256=XgmY1xeW8zrpQDJqssKamWzjn6TQ60NGNzpcdZwL6NE,3617
+trigger_loader/loader.py,sha256=wMkeZ3k36wpxt-B8OpKOa6j7z0-fnJUqQ-5AbVjNpBM,5158
+trigger_loader/processor.py,sha256=cvBfYmvcr4FLzOHgGE50oy7EkFzFaV80Z_66amqfsEY,7724
+triggerflow/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/cli.py,sha256=ZNQb3XQN8Ir6Hp6KX_ugec9bm2kqxLNZ0KdVGJmnqFA,4498
+triggerflow/core.py,sha256=QMU_zuWrYXuZekB7z8Q90Cuaga3B_uuDnYOPthQGdps,22465
+triggerflow/mlflow_wrapper.py,sha256=yCaIS-H7oC2KxnExj24ka9ylF4A1wgzRIpc7Y43ervI,10667
+triggerflow/interfaces/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/interfaces/uGT.py,sha256=UBCK0WtF-MUkI9mWrulOdExtDXgwKPsHDS4C-FXIgMs,3637
+triggerflow/starter/.gitignore,sha256=tH2z_M-tPM9MLWC2wPz1Z43Dq-wdVmb_kVYtrLT3tN4,2052
+triggerflow/starter/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/cookiecutter.json,sha256=neplzXvVe3g6OVqYD8M2olfmjRKNr1UKqmflzP3j1UY,259
+triggerflow/starter/prompts.yml,sha256=j-X_5sOsH2nvE1wg9awdNDtkNiZ7QjbvVKs9d9xyMaM,330
+triggerflow/starter/{{ cookiecutter.repo_name }}/.dvcignore,sha256=HYBS6WcsRMYtwnpN9zztNW8gy5wY0ae1qgkkkwlglYM,139
+triggerflow/starter/{{ cookiecutter.repo_name }}/.gitignore,sha256=tH2z_M-tPM9MLWC2wPz1Z43Dq-wdVmb_kVYtrLT3tN4,2052
+triggerflow/starter/{{ cookiecutter.repo_name }}/.gitlab-ci.yml,sha256=lcahT5HExM3JsqXj3u44cNEmrEl-q97JUrGxPMG6jsQ,941
+triggerflow/starter/{{ cookiecutter.repo_name }}/README.md,sha256=4t7erte67zY0Cp6qZco04EkXSXk2lb0uFVXaAx0C154,955
+triggerflow/starter/{{ cookiecutter.repo_name }}/dvc.yaml,sha256=G9TOE23-awIEt3BmMH66OCN7x04aPqFdsJDC8VbApVg,74
+triggerflow/starter/{{ cookiecutter.repo_name }}/environment.yml,sha256=J84BmAfnK_TsW7v_WifTxW9Wc9v0gX_lzmh0-c0zutI,285
+triggerflow/starter/{{ cookiecutter.repo_name }}/pyproject.toml,sha256=2maFdFnLln3Q6z8YODT2Wpw-jEi5bKN2yoC-QG3rGVM,1378
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/README.md,sha256=0jCfkFBPK5SqR2wJOKd7XTB9e1yvN0gw4D4Zi3nI8aI,1067
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/logging.yml,sha256=SaMNpZDTQhhuyCV_x6DaW1Vb8BX3WxxcV3euK98XmGg,1038
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/base/catalog.yml,sha256=Bell27MJvByOdkQmRcOoG0aKAU3hCyiy1ivws1xZcJQ,2397
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/base/parameters.yml,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/base/parameters_compile.yml,sha256=I88osguJBIfLWyKJcMZg-TOUL-HOVo0sEbro8tTndBI,392
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/base/parameters_data_processing.yml,sha256=YYWXiyHDzRnr2kIMytw_umfEpazLqPDYRG7USSPwLUo,273
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/base/parameters_load_data.yml,sha256=Jol2shPtxOEtVpju9e8xXsWkiuyuvVrdpLC0LSMezbU,235
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/base/parameters_model_training.yml,sha256=l4QPLJ66i73sZ7wT03r6aOFWzhhBIIulsBoMsBVOw-g,335
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/base/parameters_model_validation.yml,sha256=6eBMmMoTJRp0dsTo0Tdjr6Mig3BrrBSlIs_ZN98hyPQ,242
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/local/catalog.yml,sha256=Bell27MJvByOdkQmRcOoG0aKAU3hCyiy1ivws1xZcJQ,2397
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/local/parameters.yml,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/local/parameters_compile.yml,sha256=yDB39m9OszZaqX67RgcUcwh37EHGWfJAp_WRblwNFI4,397
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/local/parameters_data_processing.yml,sha256=ABcV4sNpIAwsSkkbTk27wIcE_5QEDpaGix1t34mMvjk,278
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/local/parameters_load_data.yml,sha256=fDn4tpNdgwSl-mC6-nUZP_bykj08eeEAt8XrEfHEuzY,240
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/local/parameters_model_training.yml,sha256=l4QPLJ66i73sZ7wT03r6aOFWzhhBIIulsBoMsBVOw-g,335
+triggerflow/starter/{{ cookiecutter.repo_name }}/conf/local/parameters_model_validation.yml,sha256=zroINrWbzGvp1A2TiYdO_bp8LuPav0fIpVa1fbK8dGc,244
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/01_raw/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/01_raw/samples.json,sha256=-gLHehOyK7ziLMRNe2px7f56SlWr3n1du1L6XgdbI5o,375
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/01_raw/samples_dummy.json,sha256=QX17MFlxXOObx5ghl-imT82jVHCojSZKlytO0uw1fJM,707
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/02_loaded/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/03_preprocessed/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/04_models/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/05_validation/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/06_compile/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/data/07_reporting/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/__init__.py,sha256=a-MTXhipkVaDsY3XW0DVoRSmAxbE4_NRNQo7lT4IqsM,59
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/__main__.py,sha256=YGS0Nx3OcMauvo68ReZhvznjKK_XoEUzLcnTdP1806g,659
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipeline_registry.py,sha256=LZHowiYdVJu2N1I0G2u2l7IcTU44FM8a4u_EAXZBpTk,435
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/settings.py,sha256=TRMhMNzWwELn7LuO3Xswbrcidxb4uP-0-YhvCSgglFg,1648
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/datasets/any_object.py,sha256=0y5nOkz17N8rr8b8U053eOQ2DUmPakAhdBfJmvd-npQ,367
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/datasets/base_dataset.py,sha256=VZityUPdOigfGrqj9TMT5DtyYpMS5jXfoBmlfRGmF5Q,4972
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/datasets/meta_dataset.py,sha256=siI8gyGvIKMd4DCtKm2wJftl5a5zo1HlO5s3WOzLw5U,2785
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/datasets/{{ cookiecutter.python_package }}_dataset.py,sha256=VLj4E7hsxZwswVKxyPCYrCzJ5ZCunSvNyijCWHzrPUo,936
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/models/base_model.py,sha256=PJ1S_1qIk8UyMvoGEY7UiHE7nilE4xrnwWVY9gPRh_k,4788
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/models/{{ cookiecutter.python_package }}_model.py,sha256=VkHps3wrtQcfM-CA_Ic6fsw-VSJv_FZcrSRfIKBJ1Xs,419
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/compile/__init__.py,sha256=X2jAlHHzleo1Pb9hKoh4aHOo3L6BqrnlsAxA4AVBfMM,168
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/compile/nodes.py,sha256=A9_Eoky7BWXTgvEiZUqUUdtX0mrUH7joNOof-en1MH8,1414
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/compile/pipeline.py,sha256=yeWpTxOxSONbF-pUW1bipqSgMLabWIWIe9nVdTkzG0E,207
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/data_processing/__init__.py,sha256=Eflz9--0_L6PipS2SW9vmSKR3g0yZBjxbEnNoZ9bjQM,176
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/data_processing/nodes.py,sha256=bmn-GeSQ54V2Tz5iz9Cb8MnhQXAcDlGecOiWn847su0,1053
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/data_processing/pipeline.py,sha256=PjFIWN0esIMUQ2-b1fz2FZNY7Tbn5tymBW6tF57Tm04,989
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/load_data/__init__.py,sha256=M4_hXNbopG9IGnCLazqQLMT5yjMoNdUbyimcmaIFX0U,175
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/load_data/nodes.py,sha256=so7UHCsivnIT6K2p-Gw9JBuiD_7BQOTRpKJ4eVMtVt8,319
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/load_data/pipeline.py,sha256=f2GVZNZWfKXaeHCJmBnoU4ljJ_wCfIc670z0r2dTSjU,607
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/model_training/__init__.py,sha256=M4_hXNbopG9IGnCLazqQLMT5yjMoNdUbyimcmaIFX0U,175
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/model_training/nodes.py,sha256=f38DDVELduNOoJGzHhw8P-XQZ4151B6pee6iDb1WqHM,883
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/model_training/pipeline.py,sha256=5LIoAo2CQGyeGIvcsSXOXP1CIJqdk_MlKZPfdHo8Ax4,700
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/model_validation/__init__.py,sha256=uHp2bxK1LF7_NXcftYOb1wb4QU41_cGL_VV2-J18lJw,177
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/model_validation/nodes.py,sha256=Kk6Fybq-w6EnBB14bdn-MLjbm_eigLlgFn_LVrnplCE,615
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/pipelines/model_validation/pipeline.py,sha256=iUhZhIJ2waEQpCxn6iGEaM28VTtAC47gUww_DkQ-VIo,654
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/utils/metric.py,sha256=nS5PCf2VaLlgl44uqAcz-PraQ3GW53coeVbuG9c19R0,82
+triggerflow/starter/{{ cookiecutter.repo_name }}/src/{{ cookiecutter.python_package }}/utils/plotting.py,sha256=YkB8bll9dtRiQ0gIbLDdKR2afG6OYVrFmhLwPP60oJ8,18527
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/test_run.py,sha256=aGLSgzTBQGKPcezqsMDmxMj3vNZBV7VTaPwpd4XwIrQ,912
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/compile/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/compile/test_pipeline.py,sha256=bhbQ8Pteov85kD_4rH6oaJFmxoO--zgE5BWBwv7bYog,290
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/data_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/data_processing/test_pipeline.py,sha256=LhrGZ619rDs3Mr2wsR6iysATVYj9pSBrsBJZrtlhGUg,298
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/load_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/load_data/test_pipeline.py,sha256=BlPsVwdspuEuQwvyVcPztAQFN6aSo1Z0Y1WK4BBJbhk,292
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/model_training/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/model_training/test_pipeline.py,sha256=0N747l50lEmjAgCy9K8LrNMW436edMUMo1E7tS4MADY,297
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/model_validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+triggerflow/starter/{{ cookiecutter.repo_name }}/tests/pipelines/model_validation/test_pipeline.py,sha256=2BTupcyuFEXTyMrGLVmF6Yv0CAZcdedc7fxEfmLGmxo,299
+triggerflow/templates/build_ugt.tcl,sha256=P1y42s9Ju6zDyRskCVlD-vSnblAmTafw7Jpzsq4_HWA,1061
+triggerflow/templates/data_types.h,sha256=m7_jLsRixSVjp8auxHZUUNAcSO777C5TTZl__9ENk90,12640
+triggerflow/templates/makefile,sha256=A-aetsLC51Bop0T_-yPY8Z8Hg29ApN4YPvKx_jjPuHw,970
+triggerflow/templates/makefile_version,sha256=6kFc_u2oiM9l2rH7RK_BLzdZu1ZEK8PQTQKGBLRY0v4,328
+triggerflow/templates/model-gt.cpp,sha256=qZwuTtsvrKB_mOB-HDb2uOD7mDo4-20EjFiQzRjMdPo,2969
+triggerflow/templates/model_template.cpp,sha256=jMNRcO7NgC6I9Wd2BV3Bim-P1qPsAl_oeVQ8KofQGEw,1807
+triggerflow/templates/scales.h,sha256=MFcB5S0DEvfzHuUhyZqILR0O4ktugOG-fLnuCDUUewM,373
+triggerflow-0.2.4.dist-info/METADATA,sha256=wa26vICKVPibMc7wxqLiJiwn-apZoMxBxAFqKDGA-II,5535
+triggerflow-0.2.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+triggerflow-0.2.4.dist-info/entry_points.txt,sha256=5QSV9YDseB_FqgVh9q10BdL4b1I6t68rGwPLXgVL60g,53
+triggerflow-0.2.4.dist-info/top_level.txt,sha256=cX0jkuM9tfxGp002ZBQ1AYgx-6D_NgBtomgPL0WA9bE,43
+triggerflow-0.2.4.dist-info/RECORD,,

triggerflow-0.2.4.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+triggerflow = triggerflow.cli:main

triggerflow-0.2.4.dist-info/top_level.txt

@@ -0,0 +1,3 @@
+trigger_dataset
+trigger_loader
+triggerflow

triggerflow-0.1.4.dist-info/METADATA

@@ -1,61 +0,0 @@
-Metadata-Version: 2.4
-Name: triggerflow
-Version: 0.1.4
-Summary: Utilities for ML models targeting hardware triggers
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-Requires-Dist: mlflow>=2.0
-
-# Machine Learning for Hardware Triggers
-
-`triggerflow` provides a set of utilities for Machine Learning models targeting FPGA deployment. 
-The `TriggerModel` class consolidates several Machine Learning frontends and compiler backends to construct a "trigger model". MLflow utilities are for logging, versioning, and loading of trigger models.
-
-## Installation
-
-```bash
-pip install triggerflow
-```
-
-## Usage
-
-```python
-
-from triggerflow.core import TriggerModel 
-
-trigger_model = TriggerModel(name="my-trigger-model", ml_backend="Keras", compiler="hls4ml", model, compiler_config or None)
-trigger_model() # call the constructor
-
-# then:
-output_software = trigger_model.software_predict(input_data)
-output_firmware = trigger_model.firmware_predict(input_data)
-output_qonnx = trigger_model.qonnx_predict(input_data)
-
-# save and load trigger models:
-trigger_model.save("trigger_model.tar.xz")
-
-# in a separate session:
-from trigger_model.core import TriggerModel 
-trigger_model = TriggerModel.load("trigger_model.tar.xz")
-```
-
-## Logging with MLflow
-
-```python
-# logging with MLFlow:
-import mlflow
-from trigger_model.mlflow_wrapper import log_model
-
-mlflow.set_tracking_uri("https://ngt.cern.ch/models")
-experiment_id = mlflow.create_experiment("example-experiment")
-
-with mlflow.start_run(run_name="trial-v1", experiment_id=experiment_id):
-    log_model(trigger_model, registered_model_name="TriggerModel")
-```
-
-### Note: This package doesn't install dependencies so it won't disrupt specific training environments or custom compilers. For a reference environment, see `environment.yml`.
-
-

triggerflow-0.1.4.dist-info/RECORD

@@ -1,11 +0,0 @@
-triggerflow/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-triggerflow/core.py,sha256=8yxV3xH3SjixyDx3OP0fHEtGjteMUA01MIGrdofsusg,20349
-triggerflow/mlflow_wrapper.py,sha256=mtg2mQTRlYkv9ojO6aRZ5Oln9lbE6AYA220Zw4rdEzM,3888
-triggerflow/templates/makefile,sha256=VL39isTUBewrs8zTSDzdP6LLln7zpGoCZnLadpMu7CA,808
-triggerflow/templates/makefile_version,sha256=Tmu0tyAopJbiBQVMMOa6l2Cz5GkEn20mwgzIi0CfhyM,338
-triggerflow/templates/model_template.cpp,sha256=eGwY5ca_HgjoIvqorOBPSJspP0wngpjJheq3meb48r4,1616
-triggerflow/templates/scales.h,sha256=5bq6lVF36SRQKE2zg9RpBG6K5orpPlnJ8g125nbtFow,365
-triggerflow-0.1.4.dist-info/METADATA,sha256=R5p0NDzGnDhROZLRAdWbY_JBE9EPS1dma1UWaMoQ5Ac,1942
-triggerflow-0.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-triggerflow-0.1.4.dist-info/top_level.txt,sha256=g4M0nqpVPFZcmVmsoLExDtJFLDBK4fzobCIBqo13BEw,12
-triggerflow-0.1.4.dist-info/RECORD,,

triggerflow-0.1.4.dist-info/top_level.txt

@@ -1 +0,0 @@
-triggerflow