administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-02-08 04:05:26 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

applied ruff formating

Browse Source
This commit is contained in:
Indrek Mandre 2024-02-09 17:00:23 +02:00
parent 8c96d3a02c
commit 128ed4d2bb
3 changed files with 122 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
frigate/detectors/plugins/onnx.py
View File

@ -17,9 +17,11 @@ logger = logging.getLogger(__name__)
DETECTOR_KEY = "onnx"
class ONNXDetectorConfig(BaseDetectorConfig):
type: Literal[DETECTOR_KEY]
class ONNXDetector(DetectionApi):
type_key = DETECTOR_KEY
@ -34,12 +36,23 @@ class ONNXDetector(DetectionApi):
)
raise
assert detector_config.model.model_type == 'yolov8', "ONNX: detector_config.model.model_type: only yolov8 supported"
assert detector_config.model.input_tensor == 'nhwc', "ONNX: detector_config.model.input_tensor: only nhwc supported"
if detector_config.model.input_pixel_format != 'rgb':
logger.warn("ONNX: detector_config.model.input_pixel_format: should be 'rgb' for yolov8, but '{detector_config.model.input_pixel_format}' specified!")
assert (
detector_config.model.model_type == "yolov8"
), "ONNX: detector_config.model.model_type: only yolov8 supported"
assert (
detector_config.model.input_tensor == "nhwc"
), "ONNX: detector_config.model.input_tensor: only nhwc supported"
if detector_config.model.input_pixel_format != "rgb":
logger.warn(
"ONNX: detector_config.model.input_pixel_format: should be 'rgb' for yolov8, but '{detector_config.model.input_pixel_format}' specified!"
)
assert detector_config.model.path is not None, "ONNX: No model.path configured, please configure model.path and model.labelmap_path; some suggestions: " + ', '.join(glob.glob("/config/model_cache/yolov8/*.onnx")) + " and " + ', '.join(glob.glob("/config/model_cache/yolov8/*_labels.txt"))
assert detector_config.model.path is not None, (
"ONNX: No model.path configured, please configure model.path and model.labelmap_path; some suggestions: "
+ ", ".join(glob.glob("/config/model_cache/yolov8/*.onnx"))
+ " and "
+ ", ".join(glob.glob("/config/model_cache/yolov8/*_labels.txt"))
)
path = detector_config.model.path
logger.info(f"ONNX: loading {detector_config.model.path}")
@ -55,4 +68,3 @@ class ONNXDetector(DetectionApi):
tensor_output = self.model.run(None, {model_input_name: tensor_input})[0]
return yolov8_postprocess(model_input_shape, tensor_output)

93
frigate/detectors/plugins/rocm.py
View File

@ -18,33 +18,47 @@ logger = logging.getLogger(__name__)
DETECTOR_KEY = "rocm"
def detect_gfx_version():
return subprocess.getoutput("unset HSA_OVERRIDE_GFX_VERSION && /opt/rocm/bin/rocminfo | grep gfx |head -1|awk '{print $2}'")
return subprocess.getoutput(
"unset HSA_OVERRIDE_GFX_VERSION && /opt/rocm/bin/rocminfo | grep gfx |head -1|awk '{print $2}'"
)
def auto_override_gfx_version():
# If environment varialbe already in place, do not override
gfx_version = detect_gfx_version()
old_override = os.getenv('HSA_OVERRIDE_GFX_VERSION')
if old_override not in (None, ''):
logger.warning(f"AMD/ROCm: detected {gfx_version} but HSA_OVERRIDE_GFX_VERSION already present ({old_override}), not overriding!")
old_override = os.getenv("HSA_OVERRIDE_GFX_VERSION")
if old_override not in (None, ""):
logger.warning(
f"AMD/ROCm: detected {gfx_version} but HSA_OVERRIDE_GFX_VERSION already present ({old_override}), not overriding!"
)
return old_override
mapping = {
'gfx90c': '9.0.0',
'gfx1031': '10.3.0',
'gfx1103': '11.0.0',
"gfx90c": "9.0.0",
"gfx1031": "10.3.0",
"gfx1103": "11.0.0",
}
override = mapping.get(gfx_version)
if override is not None:
logger.warning(f"AMD/ROCm: detected {gfx_version}, overriding HSA_OVERRIDE_GFX_VERSION={override}")
os.putenv('HSA_OVERRIDE_GFX_VERSION', override)
logger.warning(
f"AMD/ROCm: detected {gfx_version}, overriding HSA_OVERRIDE_GFX_VERSION={override}"
)
os.putenv("HSA_OVERRIDE_GFX_VERSION", override)
return override
return ''
return ""
class ROCmDetectorConfig(BaseDetectorConfig):
type: Literal[DETECTOR_KEY]
conserve_cpu: bool = Field(default=True, title="Conserve CPU at the expense of latency (and reduced max throughput)")
auto_override_gfx: bool = Field(default=True, title="Automatically detect and override gfx version")
conserve_cpu: bool = Field(
default=True,
title="Conserve CPU at the expense of latency (and reduced max throughput)",
)
auto_override_gfx: bool = Field(
default=True, title="Automatically detect and override gfx version"
)
class ROCmDetector(DetectionApi):
type_key = DETECTOR_KEY
@ -59,24 +73,33 @@ class ROCmDetector(DetectionApi):
logger.info(f"AMD/ROCm: loaded migraphx module")
except ModuleNotFoundError:
logger.error(
"AMD/ROCm: module loading failed, missing ROCm environment?"
)
logger.error("AMD/ROCm: module loading failed, missing ROCm environment?")
raise
if detector_config.conserve_cpu:
logger.info(f"AMD/ROCm: switching HIP to blocking mode to conserve CPU")
ctypes.CDLL('/opt/rocm/lib/libamdhip64.so').hipSetDeviceFlags(4)
assert detector_config.model.model_type == 'yolov8', "AMD/ROCm: detector_config.model.model_type: only yolov8 supported"
assert detector_config.model.input_tensor == 'nhwc', "AMD/ROCm: detector_config.model.input_tensor: only nhwc supported"
if detector_config.model.input_pixel_format != 'rgb':
logger.warn("AMD/ROCm: detector_config.model.input_pixel_format: should be 'rgb' for yolov8, but '{detector_config.model.input_pixel_format}' specified!")
ctypes.CDLL("/opt/rocm/lib/libamdhip64.so").hipSetDeviceFlags(4)
assert (
detector_config.model.model_type == "yolov8"
), "AMD/ROCm: detector_config.model.model_type: only yolov8 supported"
assert (
detector_config.model.input_tensor == "nhwc"
), "AMD/ROCm: detector_config.model.input_tensor: only nhwc supported"
if detector_config.model.input_pixel_format != "rgb":
logger.warn(
"AMD/ROCm: detector_config.model.input_pixel_format: should be 'rgb' for yolov8, but '{detector_config.model.input_pixel_format}' specified!"
)
assert detector_config.model.path is not None, "No model.path configured, please configure model.path and model.labelmap_path; some suggestions: " + ', '.join(glob.glob("/config/model_cache/yolov8/*.onnx")) + " and " + ', '.join(glob.glob("/config/model_cache/yolov8/*_labels.txt"))
assert detector_config.model.path is not None, (
"No model.path configured, please configure model.path and model.labelmap_path; some suggestions: "
+ ", ".join(glob.glob("/config/model_cache/yolov8/*.onnx"))
+ " and "
+ ", ".join(glob.glob("/config/model_cache/yolov8/*_labels.txt"))
)
path = detector_config.model.path
mxr_path = os.path.splitext(path)[0] + '.mxr'
if path.endswith('.mxr'):
mxr_path = os.path.splitext(path)[0] + ".mxr"
if path.endswith(".mxr"):
logger.info(f"AMD/ROCm: loading parsed model from {mxr_path}")
self.model = migraphx.load(mxr_path)
elif os.path.exists(mxr_path):
@ -84,30 +107,38 @@ class ROCmDetector(DetectionApi):
self.model = migraphx.load(mxr_path)
else:
logger.info(f"AMD/ROCm: loading model from {path}")
if path.endswith('.onnx'):
if path.endswith(".onnx"):
self.model = migraphx.parse_onnx(path)
elif path.endswith('.tf') or path.endswith('.tf2') or path.endswith('.tflite'):
elif (
path.endswith(".tf")
or path.endswith(".tf2")
or path.endswith(".tflite")
):
# untested
self.model = migraphx.parse_tf(path)
else:
raise Exception(f"AMD/ROCm: unkown model format {path}")
logger.info(f"AMD/ROCm: compiling the model")
self.model.compile(migraphx.get_target('gpu'), offload_copy=True, fast_math=True)
self.model.compile(
migraphx.get_target("gpu"), offload_copy=True, fast_math=True
)
logger.info(f"AMD/ROCm: saving parsed model into {mxr_path}")
os.makedirs("/config/model_cache/rocm", exist_ok=True)
migraphx.save(self.model, mxr_path)
logger.info(f"AMD/ROCm: model loaded")
def detect_raw(self, tensor_input):
model_input_name = self.model.get_parameter_names()[0];
model_input_shape = tuple(self.model.get_parameter_shapes()[model_input_name].lens());
model_input_name = self.model.get_parameter_names()[0]
model_input_shape = tuple(
self.model.get_parameter_shapes()[model_input_name].lens()
)
tensor_input = preprocess(tensor_input, model_input_shape, np.float32)
detector_result = self.model.run({model_input_name: tensor_input})[0]
addr = ctypes.cast(detector_result.data_ptr(), ctypes.POINTER(ctypes.c_float))
tensor_output = np.ctypeslib.as_array(addr, shape=detector_result.get_shape().lens())
tensor_output = np.ctypeslib.as_array(
addr, shape=detector_result.get_shape().lens()
)
return yolov8_postprocess(model_input_shape, tensor_output)

53
frigate/detectors/util.py
View File

@ -5,30 +5,50 @@ import cv2
logger = logging.getLogger(__name__)
def preprocess(tensor_input, model_input_shape, model_input_element_type):
model_input_shape = tuple(model_input_shape)
assert tensor_input.dtype == np.uint8, f'tensor_input.dtype: {tensor_input.dtype}'
assert tensor_input.dtype == np.uint8, f"tensor_input.dtype: {tensor_input.dtype}"
if len(tensor_input.shape) == 3:
tensor_input = tensor_input[np.newaxis, :]
if model_input_element_type == np.uint8:
# nothing to do for uint8 model input
assert model_input_shape == tensor_input.shape, f'model_input_shape: {model_input_shape}, tensor_input.shape: {tensor_input.shape}'
assert (
model_input_shape == tensor_input.shape
), f"model_input_shape: {model_input_shape}, tensor_input.shape: {tensor_input.shape}"
return tensor_input
assert model_input_element_type == np.float32, f'model_input_element_type: {model_input_element_type}'
assert (
model_input_element_type == np.float32
), f"model_input_element_type: {model_input_element_type}"
# tensor_input must be nhwc
assert tensor_input.shape[3] == 3, f'tensor_input.shape: {tensor_input.shape}'
assert tensor_input.shape[3] == 3, f"tensor_input.shape: {tensor_input.shape}"
if tensor_input.shape[1:3] != model_input_shape[2:4]:
logger.warn(f"preprocess: tensor_input.shape {tensor_input.shape} and model_input_shape {model_input_shape} do not match!")
logger.warn(
f"preprocess: tensor_input.shape {tensor_input.shape} and model_input_shape {model_input_shape} do not match!"
)
# cv2.dnn.blobFromImage is faster than numpying it
return cv2.dnn.blobFromImage(tensor_input[0], 1.0 / 255, (model_input_shape[3], model_input_shape[2]), None, swapRB=False)
return cv2.dnn.blobFromImage(
tensor_input[0],
1.0 / 255,
(model_input_shape[3], model_input_shape[2]),
None,
swapRB=False,
)
def yolov8_postprocess(model_input_shape, tensor_output, box_count = 20, score_threshold = 0.5, nms_threshold = 0.5):
def yolov8_postprocess(
model_input_shape,
tensor_output,
box_count=20,
score_threshold=0.5,
nms_threshold=0.5,
):
model_box_count = tensor_output.shape[2]
probs = tensor_output[0, 4:, :]
all_ids = np.argmax(probs, axis=0)
all_confidences = probs.T[np.arange(model_box_count), all_ids]
all_boxes = tensor_output[0, 0:4, :].T
mask = (all_confidences > score_threshold)
mask = all_confidences > score_threshold
class_ids = all_ids[mask]
confidences = all_confidences[mask]
cx, cy, w, h = all_boxes[mask].T
@ -37,7 +57,17 @@ def yolov8_postprocess(model_input_shape, tensor_output, box_count = 20, score_t
scale_y, scale_x = 1 / model_input_shape[1], 1 / model_input_shape[2]
else:
scale_y, scale_x = 1 / model_input_shape[2], 1 / model_input_shape[3]
detections = np.stack((class_ids, confidences, scale_y * (cy - h / 2), scale_x * (cx - w / 2), scale_y * (cy + h / 2), scale_x * (cx + w / 2)), axis=1)
detections = np.stack(
(
class_ids,
confidences,
scale_y * (cy - h / 2),
scale_x * (cx - w / 2),
scale_y * (cy + h / 2),
scale_x * (cx + w / 2),
),
axis=1,
)
if detections.shape[0] > box_count:
# if too many detections, do nms filtering to suppress overlapping boxes
boxes = np.stack((cx - w / 2, cy - h / 2, w, h), axis=1)
@ -45,8 +75,9 @@ def yolov8_postprocess(model_input_shape, tensor_output, box_count = 20, score_t
detections = detections[indexes]
# if still too many, trim the rest by confidence
if detections.shape[0] > box_count:
detections = detections[np.argpartition(detections[:,1], -box_count)[-box_count:]]
detections = detections[
np.argpartition(detections[:, 1], -box_count)[-box_count:]
]
detections = detections.copy()
detections.resize((box_count, 6))
return detections