🧹 Enable more ruff rules (#221)

* enable pycodestyle

Signed-off-by: Ashwin Vaidya <ashwinnitinvaidya@gmail.com>

* enable more rules

Signed-off-by: Ashwin Vaidya <ashwinnitinvaidya@gmail.com>

* disable pyupgrade

Signed-off-by: Ashwin Vaidya <ashwinnitinvaidya@gmail.com>

* Fix incorrect type check in ListValue validation

Signed-off-by: Ashwin Vaidya <ashwinnitinvaidya@gmail.com>

---------

Signed-off-by: Ashwin Vaidya <ashwinnitinvaidya@gmail.com>

model_api/python/model_api/adapters/inference_adapter.py

@@ -5,7 +5,7 @@
 
 from abc import ABC, abstractmethod
 from dataclasses import dataclass, field
-from typing import Any, Dict, List, Set, Tuple
+from typing import Any
 
 
 @dataclass

model_api/python/model_api/adapters/openvino_adapter.py

@@ -301,7 +301,7 @@ def await_any(self) -> None:
     def _get_meta_from_ngraph(self, layers_info):
         for node in self.model.get_ordered_ops():
             layer_name = node.get_friendly_name()
-            if layer_name not in layers_info.keys():
+            if layer_name not in layers_info:
                 continue
             layers_info[layer_name].meta = node.get_attributes()
             layers_info[layer_name].type = node.get_type_name()
@@ -339,9 +339,9 @@ def embed_preprocessing(
         ppp = PrePostProcessor(self.model)
 
         # Change the input type to the 8-bit image
-        if dtype == int:
+        if dtype is int:
             ppp.input(input_idx).tensor().set_element_type(Type.u8)
-        elif dtype == float:
+        elif dtype is float:
             ppp.input(input_idx).tensor().set_element_type(Type.f32)
 
         ppp.input(input_idx).tensor().set_layout(ov.Layout("NHWC")).set_color_format(

model_api/python/model_api/adapters/ovms_adapter.py

@@ -185,7 +185,7 @@ def _verify_model_available(client, model_name, model_version):
 def _prepare_inputs(dict_data, inputs_meta):
     inputs = {}
     for input_name, input_data in dict_data.items():
-        if input_name not in inputs_meta.keys():
+        if input_name not in inputs_meta:
             raise ValueError("Input data does not match model inputs")
         input_info = inputs_meta[input_name]
         model_precision = _tf2np_precision[input_info["dtype"]]

model_api/python/model_api/adapters/utils.py

@@ -6,8 +6,8 @@
 from __future__ import annotations  # TODO: remove when Python3.9 support is dropped
 
 import math
+from collections.abc import Callable
 from functools import partial
-from typing import Callable, Optional
 
 import cv2
 import numpy as np

model_api/python/model_api/models/action_classification.py

@@ -99,7 +99,10 @@ def parameters(cls) -> dict[str, Any]:
                     description="Path to file with labels. Overrides the labels, if they sets via 'labels' parameter",
                 ),
                 "mean_values": ListValue(
-                    description="Normalization values, which will be subtracted from image channels for image-input layer during preprocessing",
+                    description=(
+                        "Normalization values, which will be subtracted from image channels "
+                        "for image-input layer during preprocessing"
+                    ),
                     default_value=[],
                 ),
                 "pad_value": NumericalValue(

model_api/python/model_api/models/classification.py

@@ -374,7 +374,11 @@ def resolve_labels(self, predictions):
         """
 
         def get_predecessors(lbl, candidates):
-            """Returns all the predecessors of the input label or an empty list if one of the predecessors is not a candidate."""
+            """Return all predecessors.
+
+            Returns all the predecessors of the input label or an empty list if one of the predecessors is not a
+            candidate.
+            """
             predecessors = []
 
             last_parent = self.label_tree.get_parent(lbl)
@@ -517,7 +521,8 @@ def _resolve_exclusive_labels(
         For labels in `label_to_probability` sets labels that are most likely (maximum probability) in their exclusive
         group to 1.0 and other (non-max) labels to probability 0.
         """
-        # actual exclusive group selection should happen when extracting initial probs (apply argmax to exclusive groups)
+        # actual exclusive group selection should happen when extracting initial probs
+        # (apply argmax to exclusive groups)
         hard_classification = {}
         for label, probability in label_to_probability.items():
             hard_classification[label] = float(probability > 0.0)

model_api/python/model_api/models/image_model.py

@@ -90,7 +90,10 @@ def parameters(cls):
                     default_value=False,
                 ),
                 "mean_values": ListValue(
-                    description="Normalization values, which will be subtracted from image channels for image-input layer during preprocessing",
+                    description=(
+                        "Normalization values, which will be subtracted from image "
+                        "channels for image-input layer during preprocessing"
+                    ),
                     default_value=[],
                 ),
                 "orig_height": NumericalValue(

model_api/python/model_api/models/instance_segmentation.py

@@ -207,9 +207,8 @@ def postprocess(self, outputs, meta):
                         output_mask,
                     ),
                 )
-            if has_feature_vector_name:
-                if confidence > self.confidence_threshold:
-                    saliency_maps[cls - 1].append(resized_mask)
+            if has_feature_vector_name and confidence > self.confidence_threshold:
+                saliency_maps[cls - 1].append(resized_mask)
         return InstanceSegmentationResult(
             objects,
             _average_and_normalize(saliency_maps),

model_api/python/model_api/models/model.py

@@ -5,7 +5,6 @@
 
 import logging as log
 import re
-from abc import ABC
 from contextlib import contextmanager
 
 from model_api.adapters.inference_adapter import InferenceAdapter
@@ -135,9 +134,11 @@ def create_model(
 
         Args:
             model (str): model name from OpenVINO Model Zoo, path to model, OVMS URL
-            configuration (:obj:`dict`, optional): dictionary of model config with model properties, for example confidence_threshold, labels
+            configuration (:obj:`dict`, optional): dictionary of model config with model properties, for example
+                confidence_threshold, labels
             model_type (:obj:`str`, optional): name of model wrapper to create (e.g. "ssd")
-            preload (:obj:`bool`, optional): whether to call load_model(). Can be set to false to reshape model before loading
+            preload (:obj:`bool`, optional): whether to call load_model(). Can be set to false to reshape model before
+                loading.
             core (optional): openvino.Core instance, passed to OpenvinoAdapter
             weights_path (:obj:`str`, optional): path to .bin file with model weights
             adaptor_parameters (:obj:`dict`, optional): parameters of ModelAdaptor
@@ -147,7 +148,8 @@ def create_model(
             max_num_requests (:obj:`int`, optional): number of infer requests for asynchronous inference
             precision (:obj:`str`, optional): inference precision (e.g. "FP16")
             download_dir (:obj:`str`, optional): directory where to store downloaded models
-            cache_dir (:obj:`str`, optional): directory where to store compiled models to reduce the load time before the inference
+            cache_dir (:obj:`str`, optional): directory where to store compiled models to reduce the load time before
+                the inference.
 
         Returns:
             Model object
@@ -482,11 +484,13 @@ def log_layers_info(self):
         """Prints the shape, precision and layout for all model inputs/outputs."""
         for name, metadata in self.inputs.items():
             self.logger.info(
-                f"\tInput layer: {name}, shape: {metadata.shape}, precision: {metadata.precision}, layout: {metadata.layout}",
+                f"\tInput layer: {name}, shape: {metadata.shape}, "
+                f"precision: {metadata.precision}, layout: {metadata.layout}",
             )
         for name, metadata in self.outputs.items():
             self.logger.info(
-                f"\tOutput layer: {name}, shape: {metadata.shape}, precision: {metadata.precision}, layout: {metadata.layout}",
+                f"\tOutput layer: {name}, shape: {metadata.shape}, "
+                f"precision: {metadata.precision}, layout: {metadata.layout}",
             )
 
     def save(self, xml_path, bin_path="", version="UNSPECIFIED"):

model_api/python/model_api/models/segmentation.py

@@ -99,7 +99,10 @@ def parameters(cls):
                 ),
                 "soft_threshold": NumericalValue(
                     value_type=float,
-                    description="Probability threshold value for bounding box filtering. inf value means no blurring and no soft_threshold",
+                    description=(
+                        "Probability threshold value for bounding box filtering. "
+                        "inf value means no blurring and no soft_threshold"
+                    ),
                     default_value=float("-inf"),
                 ),
                 "return_soft_prediction": BooleanValue(

model_api/python/model_api/models/types.py

@@ -69,13 +69,12 @@ def validate(self, value):
                 ),
             )
             return errors
-        if len(self.choices):
-            if value not in self.choices:
-                errors.append(
-                    ConfigurableValueError(
-                        f"Incorrect value {value}: out of allowable list - {self.choices}",
-                    ),
-                )
+        if len(self.choices) and value not in self.choices:
+            errors.append(
+                ConfigurableValueError(
+                    f"Incorrect value {value}: out of allowable list - {self.choices}",
+                ),
+            )
         if self.min is not None and value < self.min:
             errors.append(
                 ConfigurableValueError(

model_api/python/model_api/models/utils.py

@@ -47,7 +47,9 @@ class ClassificationResult(
     def __str__(self):
         labels = ", ".join(f"{idx} ({label}): {confidence:.3f}" for idx, label, confidence in self.top_labels)
         return (
-            f"{labels}, [{','.join(str(i) for i in self.saliency_map.shape)}], [{','.join(str(i) for i in self.feature_vector.shape)}], "
+            f"{labels}, "
+            f"[{','.join(str(i) for i in self.saliency_map.shape)}], "
+            f"[{','.join(str(i) for i in self.feature_vector.shape)}], "
             f"[{','.join(str(i) for i in self.raw_scores.shape)}]"
         )
 
@@ -76,7 +78,9 @@ def __str__(self):
         obj_str = "; ".join(str(obj) for obj in self.objects)
         if obj_str:
             obj_str += "; "
-        return f"{obj_str}[{','.join(str(i) for i in self.saliency_map.shape)}]; [{','.join(str(i) for i in self.feature_vector.shape)}]"
+        saliency_map_shape = ",".join(str(i) for i in self.saliency_map.shape)
+        feature_vector_shape = ",".join(str(i) for i in self.feature_vector.shape)
+        return f"{obj_str}[{saliency_map_shape}]; [{feature_vector_shape}]"
 
 
 class SegmentedObject(Detection):
@@ -194,14 +198,18 @@ class DetectedKeypoints(NamedTuple):
     scores: np.ndarray
 
     def __str__(self):
-        return f"keypoints: {self.keypoints.shape}, keypoints_x_sum: {np.sum(self.keypoints[:, :1]):.3f}, scores: {self.scores.shape}"
+        return (
+            f"keypoints: {self.keypoints.shape}, "
+            f"keypoints_x_sum: {np.sum(self.keypoints[:, :1]):.3f}, "
+            f"scores: {self.scores.shape}"
+        )
 
 
 def add_rotated_rects(segmented_objects):
     objects_with_rects = []
     for segmented_object in segmented_objects:
         mask = segmented_object.mask.astype(np.uint8)
-        contours, hierarchies = cv2.findContours(
+        contours, _ = cv2.findContours(
             mask,
             cv2.RETR_EXTERNAL,
             cv2.CHAIN_APPROX_SIMPLE,
@@ -269,7 +277,10 @@ def __str__(self):
         for i, count in enumerate(outHist):
             if count > 0:
                 hist += f"{i}: {count[0] / self.resultImage.size:.3f}, "
-        return f"{hist}[{','.join(str(i) for i in self.soft_prediction.shape)}], [{','.join(str(i) for i in self.saliency_map.shape)}], [{','.join(str(i) for i in self.feature_vector.shape)}]"
+        soft_pred_shape = ",".join(str(i) for i in self.soft_prediction.shape)
+        saliency_map_shape = ",".join(str(i) for i in self.saliency_map.shape)
+        feature_vector_shape = ",".join(str(i) for i in self.feature_vector.shape)
+        return f"{hist}[{soft_pred_shape}], " f"[{saliency_map_shape}], " f"[{feature_vector_shape}]"
 
 
 class DetectionWithLandmarks(Detection):

model_api/python/model_api/models/visual_prompting.py

@@ -143,7 +143,8 @@ def __init__(
             encoder_model (SAMImageEncoder): initialized decoder wrapper
             decoder_model (SAMDecoder): initialized encoder wrapper
             reference_features (VisualPromptingFeatures | None, optional): Previously generated reference features.
-             Once the features are passed, one can skip learn() method, and start predicting masks right away. Defaults to None.
+                Once the features are passed, one can skip learn() method, and start predicting masks right away.
+                Defaults to None.
             threshold (float, optional): Threshold to match vs reference features on infer(). Greater value means a
             stricter matching. Defaults to 0.65.
         """
@@ -213,7 +214,8 @@ def learn(
             reset_features (bool, optional): Forces learning from scratch. Defaults to False.
 
         Returns:
-            tuple[VisualPromptingFeatures, np.ndarray]: return values are the updated VPT reference features and reference masks.
+            tuple[VisualPromptingFeatures, np.ndarray]: return values are the updated VPT reference features and
+                reference masks.
             The shape of the reference mask is N_labels x H x W, where H and W are the same as in the input image.
         """
         if boxes is None and points is None and polygons is None:
@@ -317,26 +319,32 @@ def infer(
 
         Args:
             image (np.ndarray): HWC-shaped image
-            reference_features (VisualPromptingFeatures | None, optional): Reference features object obtained during previous learn() calls.
-            If not passed, object internal state is used, which reflects the last learn() call. Defaults to None.
-            apply_masks_refinement (bool, optional): Flag controlling additional refinement stage on inference. Once enabled, decoder will
-            be launched 2 extra times to refine the masks obtained with the first decoder call. Defaults to True.
+            reference_features (VisualPromptingFeatures | None, optional): Reference features object obtained during
+                previous learn() calls. If not passed, object internal state is used, which reflects the last learn()
+                call. Defaults to None.
+            apply_masks_refinement (bool, optional): Flag controlling additional refinement stage on inference.
+            Once enabled, decoder will be launched 2 extra times to refine the masks obtained with the first decoder
+            call. Defaults to True.
 
         Returns:
-            ZSLVisualPromptingResult: Mapping label -> predicted mask. Each mask object contains a list of binary masks, and a list of
-            related prompts. Each binary mask corresponds to one prompt point. Class mask can be obtained by applying OR operation to all
-            mask corresponding to one label.
+            ZSLVisualPromptingResult: Mapping label -> predicted mask. Each mask object contains a list of binary masks,
+                and a list of related prompts. Each binary mask corresponds to one prompt point. Class mask can be
+                obtained by applying OR operation to all mask corresponding to one label.
         """
         if reference_features is None:
             if self._reference_features is None:
                 raise RuntimeError(
-                    "Reference features are not defined. This parameter can be passed via SAMLearnableVisualPrompter constructor, or as an argument of infer() method",
+                    (
+                        "Reference features are not defined. This parameter can be passed via "
+                        "SAMLearnableVisualPrompter constructor, or as an argument of infer() method"
+                    ),
                 )
             reference_feats = self._reference_features
 
             if self._used_indices is None:
                 raise RuntimeError(
-                    "Used indices are not defined. This parameter can be passed via SAMLearnableVisualPrompter constructor, or as an argument of infer() method",
+                    "Used indices are not defined. This parameter can be passed via "
+                    "SAMLearnableVisualPrompter constructor, or as an argument of infer() method"
                 )
             used_idx = self._used_indices
         else:

model_api/python/model_api/models/yolo.py

@@ -318,7 +318,7 @@ def iou(box_1, box_2):
 
     def _parse_outputs(self, outputs, meta):
         detections = []
-        for layer_name in self.yolo_layer_params.keys():
+        for layer_name in self.yolo_layer_params:
             out_blob = outputs[layer_name]
             layer_params = self.yolo_layer_params[layer_name]
             out_blob.shape = layer_params[0]
@@ -630,7 +630,10 @@ def _get_outputs(self):
                 )
         if self.outputs[bboxes_blob_name].shape[1] != self.outputs[scores_blob_name].shape[2]:
             self.raise_error(
-                f"Expected the same dimension for boxes and scores, but got {self.outputs[bboxes_blob_name].shape[1]} and {self.outputs[scores_blob_name].shape[2]}",
+                (
+                    f"Expected the same dimension for boxes and scores, but got "
+                    f"{self.outputs[bboxes_blob_name].shape[1]} and {self.outputs[scores_blob_name].shape[2]}"
+                ),
             )
         return bboxes_blob_name, scores_blob_name, indices_blob_name
 
@@ -745,7 +748,10 @@ def parameters(cls):
         parameters.update(
             {
                 "agnostic_nms": BooleanValue(
-                    description="If True, the model is agnostic to the number of classes, and all classes are considered as one",
+                    description=(
+                        "If True, the model is agnostic to the number of classes, "
+                        "and all classes are considered as one"
+                    ),
                     default_value=False,
                 ),
                 "iou_threshold": NumericalValue(

model_api/python/model_api/pipelines/async_pipeline.py

@@ -5,7 +5,7 @@
 
 from time import perf_counter
 
-from ..performance_metrics import PerformanceMetrics
+from model_api.performance_metrics import PerformanceMetrics
 
 
 class AsyncPipeline: