diff --git a/model_api/python/model_api/models/keypoint_detection.py b/model_api/python/model_api/models/keypoint_detection.py
index e3e8a86f..473e01a4 100644
--- a/model_api/python/model_api/models/keypoint_detection.py
+++ b/model_api/python/model_api/models/keypoint_detection.py
@@ -26,30 +26,29 @@
class KeypointDetectionModel(ImageModel):
- """
- A wrapper that implements a basic keypoint regression model.
- """
+ """A wrapper that implements a basic keypoint regression model."""
__model__ = "keypoint_detection"
- def __init__(self, inference_adapter, configuration=dict(), preload=False):
- """
- Initializes the keypoint detection model.
+ def __init__(self, inference_adapter, configuration: dict = {}, preload=False):
+ """Initializes the keypoint detection model.
Args:
inference_adapter (InferenceAdapter): inference adapter containing the underlying model.
configuration (dict, optional): configuration overrides the model parameters (see parameters() method).
- Defaults to dict().
+ Defaults to {}.
preload (bool, optional): forces inference adapter to load the model. Defaults to False.
"""
super().__init__(inference_adapter, configuration, preload)
self._check_io_number(1, 2)
+ self.apply_softmax: bool
def postprocess(
- self, outputs: dict[str, np.ndarray], meta: dict[str, Any]
+ self,
+ outputs: dict[str, np.ndarray],
+ meta: dict[str, Any],
) -> DetectedKeypoints:
- """
- Applies SCC decoded to the model outputs.
+ """Applies SCC decoded to the model outputs.
Args:
outputs (dict[str, np.ndarray]): raw outputs of the model
@@ -60,12 +59,26 @@ def postprocess(
"""
encoded_kps = list(outputs.values())
batch_keypoints, batch_scores = _decode_simcc(
- *encoded_kps, apply_softmax=self.apply_softmax
+ encoded_kps[0],
+ encoded_kps[1],
+ apply_softmax=self.apply_softmax,
)
orig_h, orig_w = meta["original_shape"][:2]
kp_scale_h = orig_h / self.h
kp_scale_w = orig_w / self.w
- batch_keypoints = batch_keypoints.squeeze() * np.array([kp_scale_w, kp_scale_h])
+
+ batch_keypoints = batch_keypoints.squeeze()
+
+ if self.resize_type in ["fit_to_window", "fit_to_window_letterbox"]:
+ inverted_scale = max(kp_scale_h, kp_scale_w)
+ kp_scale_h = kp_scale_w = inverted_scale
+ if self.resize_type == "fit_to_window_letterbox":
+ pad_left = (self.w - round(orig_w / inverted_scale)) // 2
+ pad_top = (self.h - round(orig_h / inverted_scale)) // 2
+ batch_keypoints -= np.array([pad_left, pad_top])
+
+ batch_keypoints *= np.array([kp_scale_w, kp_scale_h])
+
return DetectedKeypoints(batch_keypoints, batch_scores.squeeze())
@classmethod
@@ -74,13 +87,15 @@ def parameters(cls) -> dict:
parameters.update(
{
"labels": ListValue(
- description="List of class labels", value_type=str, default_value=[]
+ description="List of class labels",
+ value_type=str,
+ default_value=[],
),
"apply_softmax": BooleanValue(
default_value=True,
description="Whether to apply softmax on the heatmap.",
),
- }
+ },
)
return parameters
@@ -137,6 +152,8 @@ def _decode_simcc(
simcc_y: np.ndarray,
simcc_split_ratio: float = 2.0,
apply_softmax: bool = False,
+ decode_beta: float = 150.0,
+ sigma: float | int = 6.0,
) -> tuple[np.ndarray, np.ndarray]:
"""Decodes keypoint coordinates from SimCC representations. The decoded coordinates are in the input image space.
@@ -144,8 +161,12 @@ def _decode_simcc(
simcc_x (np.ndarray): SimCC label for x-axis
simcc_y (np.ndarray): SimCC label for y-axis
simcc_split_ratio (float): The ratio of the label size to the input size.
- apply_softmax (bool): whether to apply softmax on the heatmap.
+ apply_softmax (bool): whether to apply softmax during scores generation.
Defaults to False.
+ decode_beta (float): The beta value for decoding scores with softmax. Defaults
+ to 150.0.
+ sigma (float | int): The sigma value in the Gaussian SimCC
+ label. Defaults to 6.0
Returns:
tuple:
@@ -153,7 +174,11 @@ def _decode_simcc(
- scores (np.ndarray): The keypoint scores in shape (N, K).
It usually represents the confidence of the keypoint prediction
"""
- keypoints, scores = _get_simcc_maximum(simcc_x, simcc_y, apply_softmax)
+ keypoints, scores = _get_simcc_maximum(simcc_x, simcc_y)
+ if apply_softmax:
+ _, scores = _get_simcc_maximum(
+ decode_beta * sigma * simcc_x, decode_beta * sigma * simcc_y, apply_softmax
+ )
# Unsqueeze the instance dimension for single-instance results
if keypoints.ndim == 2:
@@ -169,6 +194,7 @@ def _get_simcc_maximum(
simcc_x: np.ndarray,
simcc_y: np.ndarray,
apply_softmax: bool = False,
+ softmax_eps: float = 1e-06,
) -> tuple[np.ndarray, np.ndarray]:
"""Get maximum response location and value from simcc representations.
@@ -183,6 +209,8 @@ def _get_simcc_maximum(
simcc_y (np.ndarray): y-axis SimCC in shape (K, Hy) or (N, K, Hy)
apply_softmax (bool): whether to apply softmax on the heatmap.
Defaults to False.
+ softmax_eps (flat): a constant to avoid division by zero in softmax.
+ Defaults to 1e-6.
Returns:
tuple:
@@ -212,17 +240,21 @@ def _get_simcc_maximum(
simcc_x = simcc_x - np.max(simcc_x, axis=1, keepdims=True)
simcc_y = simcc_y - np.max(simcc_y, axis=1, keepdims=True)
ex, ey = np.exp(simcc_x), np.exp(simcc_y)
- simcc_x = ex / np.sum(ex, axis=1, keepdims=True)
- simcc_y = ey / np.sum(ey, axis=1, keepdims=True)
+ simcc_x = ex / (np.sum(ex, axis=1, keepdims=True) + softmax_eps)
+ simcc_y = ey / (np.sum(ey, axis=1, keepdims=True) + softmax_eps)
x_locs = np.argmax(simcc_x, axis=1)
y_locs = np.argmax(simcc_y, axis=1)
locs = np.stack((x_locs, y_locs), axis=-1).astype(np.float32)
max_val_x = np.take_along_axis(
- simcc_x, np.expand_dims(x_locs, axis=-1), axis=-1
+ simcc_x,
+ np.expand_dims(x_locs, axis=-1),
+ axis=-1,
).squeeze(axis=-1)
max_val_y = np.take_along_axis(
- simcc_y, np.expand_dims(y_locs, axis=-1), axis=-1
+ simcc_y,
+ np.expand_dims(y_locs, axis=-1),
+ axis=-1,
).squeeze(axis=-1)
mask = max_val_x > max_val_y
diff --git a/model_api/python/pyproject.toml b/model_api/python/pyproject.toml
index 716053e4..96f436e4 100644
--- a/model_api/python/pyproject.toml
+++ b/model_api/python/pyproject.toml
@@ -8,7 +8,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "openvino_model_api"
-version = "0.2.5.1"
+version = "0.2.5.2"
requires-python = ">=3.9"
authors = [
{name = "Intel(R) Corporation"},
@@ -26,8 +26,8 @@ dependencies = [
"numpy>=1.16.6",
"opencv-python",
"scipy>=1.5.4",
- "openvino>=2024.0",
- "openvino-dev>=2024.0",
+ "openvino==2024.*",
+ "openvino-dev==2024.*",
"omz_tools @ git+https://github.com/openvinotoolkit/open_model_zoo.git@master#egg=omz_tools&subdirectory=tools/model_tools",
]
diff --git a/tests/python/accuracy/public_scope.json b/tests/python/accuracy/public_scope.json
index e9115dde..cac68e8e 100644
--- a/tests/python/accuracy/public_scope.json
+++ b/tests/python/accuracy/public_scope.json
@@ -429,7 +429,7 @@
"test_data": [
{
"image": "coco128/images/train2017/000000000471.jpg",
- "reference": ["keypoints: (17, 2), keypoints_x_sum: 5700.000, scores: (17,)"]
+ "reference": ["keypoints: (17, 2), keypoints_x_sum: 2930.000, scores: (17,)"]
}
]
},