Hailo Official integration (#16906)

* Adding Models

* Final Async Update

* Bug Fixing

* Fix

* Adding fixes

* Working async infer

* Final Documenatation and debug update

* Removing some extra prints

* Post-process correct label push

* config docs fix

* Review Fix

* Review fix 2.0

* Fixing the ASYNC API to work from 30ms to 10ms

* Fix for multi stream async infernce

* Format

* Fix #3

* Format#2

* Remove Unnessery includes

* Sort Imports
This commit is contained in:
OmriAx
2025-03-11 13:36:07 -06:00
committed by GitHub
parent 300f85720c
commit 7411a8bafa
5 changed files with 495 additions and 237 deletions
+390 -226
View File
@@ -1,286 +1,450 @@
import logging
import os
import queue
import subprocess
import threading
import urllib.request
from functools import partial
from typing import Dict, List, Optional, Tuple
import cv2
import numpy as np
try:
from hailo_platform import (
HEF,
ConfigureParams,
FormatType,
HailoRTException,
HailoStreamInterface,
InferVStreams,
InputVStreamParams,
OutputVStreamParams,
HailoSchedulingAlgorithm,
VDevice,
)
except ModuleNotFoundError:
pass
from pydantic import BaseModel, Field
from pydantic import Field
from typing_extensions import Literal
from frigate.const import MODEL_CACHE_DIR
from frigate.detectors.detection_api import DetectionApi
from frigate.detectors.detector_config import BaseDetectorConfig
from frigate.detectors.detector_config import (
BaseDetectorConfig,
)
# Set up logging
logger = logging.getLogger(__name__)
# Define the detector key for Hailo
# ----------------- ResponseStore Class ----------------- #
class ResponseStore:
"""
A thread-safe hash-based response store that maps request IDs
to their results. Threads can wait on the condition variable until
their request's result appears.
"""
def __init__(self):
self.responses = {} # Maps request_id -> (original_input, infer_results)
self.lock = threading.Lock()
self.cond = threading.Condition(self.lock)
def put(self, request_id, response):
with self.cond:
self.responses[request_id] = response
self.cond.notify_all()
def get(self, request_id, timeout=None):
with self.cond:
if not self.cond.wait_for(
lambda: request_id in self.responses, timeout=timeout
):
raise TimeoutError(f"Timeout waiting for response {request_id}")
return self.responses.pop(request_id)
# ----------------- Utility Functions ----------------- #
def preprocess_tensor(image: np.ndarray, model_w: int, model_h: int) -> np.ndarray:
"""
Resize an image with unchanged aspect ratio using padding.
Assumes input image shape is (H, W, 3).
"""
if image.ndim == 4 and image.shape[0] == 1:
image = image[0]
h, w = image.shape[:2]
if (w, h) == (320, 320) and (model_w, model_h) == (640, 640):
return cv2.resize(image, (model_w, model_h), interpolation=cv2.INTER_LINEAR)
scale = min(model_w / w, model_h / h)
new_w, new_h = int(w * scale), int(h * scale)
resized_image = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_CUBIC)
padded_image = np.full((model_h, model_w, 3), 114, dtype=image.dtype)
x_offset = (model_w - new_w) // 2
y_offset = (model_h - new_h) // 2
padded_image[y_offset : y_offset + new_h, x_offset : x_offset + new_w] = (
resized_image
)
return padded_image
# ----------------- Global Constants ----------------- #
DETECTOR_KEY = "hailo8l"
ARCH = None
H8_DEFAULT_MODEL = "yolov6n.hef"
H8L_DEFAULT_MODEL = "yolov6n.hef"
H8_DEFAULT_URL = "https://hailo-model-zoo.s3.eu-west-2.amazonaws.com/ModelZoo/Compiled/v2.14.0/hailo8/yolov6n.hef"
H8L_DEFAULT_URL = "https://hailo-model-zoo.s3.eu-west-2.amazonaws.com/ModelZoo/Compiled/v2.14.0/hailo8l/yolov6n.hef"
# Configuration class for model settings
class ModelConfig(BaseModel):
path: str = Field(default=None, title="Model Path") # Path to the HEF file
def detect_hailo_arch():
try:
result = subprocess.run(
["hailortcli", "fw-control", "identify"], capture_output=True, text=True
)
if result.returncode != 0:
logger.error(f"Inference error: {result.stderr}")
return None
for line in result.stdout.split("\n"):
if "Device Architecture" in line:
if "HAILO8L" in line:
return "hailo8l"
elif "HAILO8" in line:
return "hailo8"
logger.error("Inference error: Could not determine Hailo architecture.")
return None
except Exception as e:
logger.error(f"Inference error: {e}")
return None
# Configuration class for Hailo detector
class HailoDetectorConfig(BaseDetectorConfig):
type: Literal[DETECTOR_KEY] # Type of the detector
device: str = Field(default="PCIe", title="Device Type") # Device type (e.g., PCIe)
# ----------------- HailoAsyncInference Class ----------------- #
class HailoAsyncInference:
def __init__(
self,
hef_path: str,
input_queue: queue.Queue,
output_store: ResponseStore,
batch_size: int = 1,
input_type: Optional[str] = None,
output_type: Optional[Dict[str, str]] = None,
send_original_frame: bool = False,
) -> None:
self.input_queue = input_queue
self.output_store = output_store
params = VDevice.create_params()
params.scheduling_algorithm = HailoSchedulingAlgorithm.ROUND_ROBIN
self.hef = HEF(hef_path)
self.target = VDevice(params)
self.infer_model = self.target.create_infer_model(hef_path)
self.infer_model.set_batch_size(batch_size)
if input_type is not None:
self._set_input_type(input_type)
if output_type is not None:
self._set_output_type(output_type)
self.output_type = output_type
self.send_original_frame = send_original_frame
def _set_input_type(self, input_type: Optional[str] = None) -> None:
self.infer_model.input().set_format_type(getattr(FormatType, input_type))
def _set_output_type(
self, output_type_dict: Optional[Dict[str, str]] = None
) -> None:
for output_name, output_type in output_type_dict.items():
self.infer_model.output(output_name).set_format_type(
getattr(FormatType, output_type)
)
def callback(
self,
completion_info,
bindings_list: List,
input_batch: List,
request_ids: List[int],
):
if completion_info.exception:
logger.error(f"Inference error: {completion_info.exception}")
else:
for i, bindings in enumerate(bindings_list):
if len(bindings._output_names) == 1:
result = bindings.output().get_buffer()
else:
result = {
name: np.expand_dims(bindings.output(name).get_buffer(), axis=0)
for name in bindings._output_names
}
self.output_store.put(request_ids[i], (input_batch[i], result))
def _create_bindings(self, configured_infer_model) -> object:
if self.output_type is None:
output_buffers = {
output_info.name: np.empty(
self.infer_model.output(output_info.name).shape,
dtype=getattr(
np, str(output_info.format.type).split(".")[1].lower()
),
)
for output_info in self.hef.get_output_vstream_infos()
}
else:
output_buffers = {
name: np.empty(
self.infer_model.output(name).shape,
dtype=getattr(np, self.output_type[name].lower()),
)
for name in self.output_type
}
return configured_infer_model.create_bindings(output_buffers=output_buffers)
def get_input_shape(self) -> Tuple[int, ...]:
return self.hef.get_input_vstream_infos()[0].shape
def run(self) -> None:
with self.infer_model.configure() as configured_infer_model:
while True:
batch_data = self.input_queue.get()
if batch_data is None:
break
request_id, frame_data = batch_data
preprocessed_batch = [frame_data]
request_ids = [request_id]
input_batch = preprocessed_batch # non-send_original_frame mode
bindings_list = []
for frame in preprocessed_batch:
bindings = self._create_bindings(configured_infer_model)
bindings.input().set_buffer(np.array(frame))
bindings_list.append(bindings)
configured_infer_model.wait_for_async_ready(timeout_ms=10000)
job = configured_infer_model.run_async(
bindings_list,
partial(
self.callback,
input_batch=input_batch,
request_ids=request_ids,
bindings_list=bindings_list,
),
)
job.wait(100)
# Hailo detector class implementation
# ----------------- HailoDetector Class ----------------- #
class HailoDetector(DetectionApi):
type_key = DETECTOR_KEY # Set the type key to the Hailo detector key
type_key = DETECTOR_KEY
def __init__(self, detector_config: HailoDetectorConfig):
# Initialize device type and model path from the configuration
self.h8l_device_type = detector_config.device
self.h8l_model_path = detector_config.model.path
self.h8l_model_height = detector_config.model.height
self.h8l_model_width = detector_config.model.width
self.h8l_model_type = detector_config.model.model_type
self.h8l_tensor_format = detector_config.model.input_tensor
self.h8l_pixel_format = detector_config.model.input_pixel_format
self.model_url = "https://hailo-model-zoo.s3.eu-west-2.amazonaws.com/ModelZoo/Compiled/v2.11.0/hailo8l/ssd_mobilenet_v1.hef"
self.cache_dir = os.path.join(MODEL_CACHE_DIR, "h8l_cache")
self.expected_model_filename = "ssd_mobilenet_v1.hef"
output_type = "FLOAT32"
def __init__(self, detector_config: "HailoDetectorConfig"):
global ARCH
ARCH = detect_hailo_arch()
self.cache_dir = MODEL_CACHE_DIR
self.device_type = detector_config.device
self.model_height = (
detector_config.model.height
if hasattr(detector_config.model, "height")
else None
)
self.model_width = (
detector_config.model.width
if hasattr(detector_config.model, "width")
else None
)
self.model_type = (
detector_config.model.model_type
if hasattr(detector_config.model, "model_type")
else None
)
self.tensor_format = (
detector_config.model.input_tensor
if hasattr(detector_config.model, "input_tensor")
else None
)
self.pixel_format = (
detector_config.model.input_pixel_format
if hasattr(detector_config.model, "input_pixel_format")
else None
)
self.input_dtype = (
detector_config.model.input_dtype
if hasattr(detector_config.model, "input_dtype")
else None
)
self.output_type = "FLOAT32"
self.set_path_and_url(detector_config.model.path)
self.working_model_path = self.check_and_prepare()
self.batch_size = 1
self.input_queue = queue.Queue()
self.response_store = ResponseStore()
self.request_counter = 0
self.request_counter_lock = threading.Lock()
logger.info(f"Initializing Hailo device as {self.h8l_device_type}")
self.check_and_prepare_model()
try:
# Validate device type
if self.h8l_device_type not in ["PCIe", "M.2"]:
raise ValueError(f"Unsupported device type: {self.h8l_device_type}")
# Initialize the Hailo device
self.target = VDevice()
# Load the HEF (Hailo's binary format for neural networks)
self.hef = HEF(self.h8l_model_path)
# Create configuration parameters from the HEF
self.configure_params = ConfigureParams.create_from_hef(
hef=self.hef, interface=HailoStreamInterface.PCIe
logger.debug(f"[INIT] Loading HEF model from {self.working_model_path}")
self.inference_engine = HailoAsyncInference(
self.working_model_path,
self.input_queue,
self.response_store,
self.batch_size,
)
# Configure the device with the HEF
self.network_groups = self.target.configure(self.hef, self.configure_params)
self.network_group = self.network_groups[0]
self.network_group_params = self.network_group.create_params()
# Create input and output virtual stream parameters
self.input_vstream_params = InputVStreamParams.make(
self.network_group,
format_type=self.hef.get_input_vstream_infos()[0].format.type,
self.input_shape = self.inference_engine.get_input_shape()
logger.debug(f"[INIT] Model input shape: {self.input_shape}")
self.inference_thread = threading.Thread(
target=self.inference_engine.run, daemon=True
)
self.output_vstream_params = OutputVStreamParams.make(
self.network_group, format_type=getattr(FormatType, output_type)
)
# Get input and output stream information from the HEF
self.input_vstream_info = self.hef.get_input_vstream_infos()
self.output_vstream_info = self.hef.get_output_vstream_infos()
logger.info("Hailo device initialized successfully")
logger.debug(f"[__init__] Model Path: {self.h8l_model_path}")
logger.debug(f"[__init__] Input Tensor Format: {self.h8l_tensor_format}")
logger.debug(f"[__init__] Input Pixel Format: {self.h8l_pixel_format}")
logger.debug(f"[__init__] Input VStream Info: {self.input_vstream_info[0]}")
logger.debug(
f"[__init__] Output VStream Info: {self.output_vstream_info[0]}"
)
except HailoRTException as e:
logger.error(f"HailoRTException during initialization: {e}")
raise
self.inference_thread.start()
except Exception as e:
logger.error(f"Failed to initialize Hailo device: {e}")
logger.error(f"[INIT] Failed to initialize HailoAsyncInference: {e}")
raise
def check_and_prepare_model(self):
# Ensure cache directory exists
def set_path_and_url(self, path: str = None):
if not path:
self.model_path = None
self.url = None
return
if self.is_url(path):
self.url = path
self.model_path = None
else:
self.model_path = path
self.url = None
def is_url(self, url: str) -> bool:
return (
url.startswith("http://")
or url.startswith("https://")
or url.startswith("www.")
)
@staticmethod
def extract_model_name(path: str = None, url: str = None) -> str:
if path and path.endswith(".hef"):
return os.path.basename(path)
elif url and url.endswith(".hef"):
return os.path.basename(url)
else:
if ARCH == "hailo8":
return H8_DEFAULT_MODEL
else:
return H8L_DEFAULT_MODEL
@staticmethod
def download_model(url: str, destination: str):
if not url.endswith(".hef"):
raise ValueError("Invalid model URL. Only .hef files are supported.")
try:
urllib.request.urlretrieve(url, destination)
logger.debug(f"Downloaded model to {destination}")
except Exception as e:
raise RuntimeError(f"Failed to download model from {url}: {str(e)}")
def check_and_prepare(self) -> str:
if not os.path.exists(self.cache_dir):
os.makedirs(self.cache_dir)
model_name = self.extract_model_name(self.model_path, self.url)
cached_model_path = os.path.join(self.cache_dir, model_name)
if not self.model_path and not self.url:
if os.path.exists(cached_model_path):
logger.debug(f"Model found in cache: {cached_model_path}")
return cached_model_path
else:
logger.debug(f"Downloading default model: {model_name}")
if ARCH == "hailo8":
self.download_model(H8_DEFAULT_URL, cached_model_path)
else:
self.download_model(H8L_DEFAULT_URL, cached_model_path)
elif self.url:
logger.debug(f"Downloading model from URL: {self.url}")
self.download_model(self.url, cached_model_path)
elif self.model_path:
if os.path.exists(self.model_path):
logger.debug(f"Using existing model at: {self.model_path}")
return self.model_path
else:
raise FileNotFoundError(f"Model file not found at: {self.model_path}")
return cached_model_path
# Check for the expected model file
model_file_path = os.path.join(self.cache_dir, self.expected_model_filename)
if not os.path.isfile(model_file_path):
logger.info(
f"A model file was not found at {model_file_path}, Downloading one from {self.model_url}."
)
urllib.request.urlretrieve(self.model_url, model_file_path)
logger.info(f"A model file was downloaded to {model_file_path}.")
else:
logger.info(
f"A model file already exists at {model_file_path} not downloading one."
)
def _get_request_id(self) -> int:
with self.request_counter_lock:
request_id = self.request_counter
self.request_counter += 1
if self.request_counter > 1000000:
self.request_counter = 0
return request_id
def detect_raw(self, tensor_input):
logger.debug("[detect_raw] Entering function")
logger.debug(
f"[detect_raw] The `tensor_input` = {tensor_input} tensor_input shape = {tensor_input.shape}"
)
request_id = self._get_request_id()
if tensor_input is None:
raise ValueError(
"[detect_raw] The 'tensor_input' argument must be provided"
)
# Ensure tensor_input is a numpy array
if isinstance(tensor_input, list):
tensor_input = np.array(tensor_input)
logger.debug(
f"[detect_raw] Converted tensor_input to numpy array: shape {tensor_input.shape}"
)
input_data = tensor_input
logger.debug(
f"[detect_raw] Input data for inference shape: {tensor_input.shape}, dtype: {tensor_input.dtype}"
)
tensor_input = self.preprocess(tensor_input)
if isinstance(tensor_input, np.ndarray) and len(tensor_input.shape) == 3:
tensor_input = np.expand_dims(tensor_input, axis=0)
self.input_queue.put((request_id, tensor_input))
try:
with InferVStreams(
self.network_group,
self.input_vstream_params,
self.output_vstream_params,
) as infer_pipeline:
input_dict = {}
if isinstance(input_data, dict):
input_dict = input_data
logger.debug("[detect_raw] it a dictionary.")
elif isinstance(input_data, (list, tuple)):
for idx, layer_info in enumerate(self.input_vstream_info):
input_dict[layer_info.name] = input_data[idx]
logger.debug("[detect_raw] converted from list/tuple.")
else:
if len(input_data.shape) == 3:
input_data = np.expand_dims(input_data, axis=0)
logger.debug("[detect_raw] converted from an array.")
input_dict[self.input_vstream_info[0].name] = input_data
original_input, infer_results = self.response_store.get(
request_id, timeout=10.0
)
except TimeoutError:
logger.error(
f"Timeout waiting for inference results for request {request_id}"
)
return np.zeros((20, 6), dtype=np.float32)
logger.debug(
f"[detect_raw] Input dictionary for inference keys: {input_dict.keys()}"
)
if isinstance(infer_results, list) and len(infer_results) == 1:
infer_results = infer_results[0]
with self.network_group.activate(self.network_group_params):
raw_output = infer_pipeline.infer(input_dict)
logger.debug(f"[detect_raw] Raw inference output: {raw_output}")
if self.output_vstream_info[0].name not in raw_output:
logger.error(
f"[detect_raw] Missing output stream {self.output_vstream_info[0].name} in inference results"
)
return np.zeros((20, 6), np.float32)
raw_output = raw_output[self.output_vstream_info[0].name][0]
logger.debug(
f"[detect_raw] Raw output for stream {self.output_vstream_info[0].name}: {raw_output}"
)
# Process the raw output
detections = self.process_detections(raw_output)
if len(detections) == 0:
logger.debug(
"[detect_raw] No detections found after processing. Setting default values."
)
return np.zeros((20, 6), np.float32)
else:
formatted_detections = detections
if (
formatted_detections.shape[1] != 6
): # Ensure the formatted detections have 6 columns
logger.error(
f"[detect_raw] Unexpected shape for formatted detections: {formatted_detections.shape}. Expected (20, 6)."
)
return np.zeros((20, 6), np.float32)
return formatted_detections
except HailoRTException as e:
logger.error(f"[detect_raw] HailoRTException during inference: {e}")
return np.zeros((20, 6), np.float32)
except Exception as e:
logger.error(f"[detect_raw] Exception during inference: {e}")
return np.zeros((20, 6), np.float32)
finally:
logger.debug("[detect_raw] Exiting function")
def process_detections(self, raw_detections, threshold=0.5):
boxes, scores, classes = [], [], []
num_detections = 0
logger.debug(f"[process_detections] Raw detections: {raw_detections}")
for i, detection_set in enumerate(raw_detections):
threshold = 0.4
all_detections = []
for class_id, detection_set in enumerate(infer_results):
if not isinstance(detection_set, np.ndarray) or detection_set.size == 0:
logger.debug(
f"[process_detections] Detection set {i} is empty or not an array, skipping."
)
continue
logger.debug(
f"[process_detections] Detection set {i} shape: {detection_set.shape}"
)
for detection in detection_set:
if detection.shape[0] == 0:
logger.debug(
f"[process_detections] Detection in set {i} is empty, skipping."
)
for det in detection_set:
if det.shape[0] < 5:
continue
ymin, xmin, ymax, xmax = detection[:4]
score = np.clip(detection[4], 0, 1) # Use np.clip for clarity
score = float(det[4])
if score < threshold:
logger.debug(
f"[process_detections] Detection in set {i} has a score {score} below threshold {threshold}. Skipping."
)
continue
all_detections.append([class_id, score, det[0], det[1], det[2], det[3]])
logger.debug(
f"[process_detections] Adding detection with coordinates: ({xmin}, {ymin}), ({xmax}, {ymax}) and score: {score}"
)
boxes.append([ymin, xmin, ymax, xmax])
scores.append(score)
classes.append(i)
num_detections += 1
if len(all_detections) == 0:
detections_array = np.zeros((20, 6), dtype=np.float32)
else:
detections_array = np.array(all_detections, dtype=np.float32)
if detections_array.shape[0] > 20:
detections_array = detections_array[:20, :]
elif detections_array.shape[0] < 20:
pad = np.zeros((20 - detections_array.shape[0], 6), dtype=np.float32)
detections_array = np.vstack((detections_array, pad))
logger.debug(
f"[process_detections] Boxes: {boxes}, Scores: {scores}, Classes: {classes}, Num detections: {num_detections}"
)
return detections_array
if num_detections == 0:
logger.debug("[process_detections] No valid detections found.")
return np.zeros((20, 6), np.float32)
combined = np.hstack(
(
np.array(classes)[:, np.newaxis],
np.array(scores)[:, np.newaxis],
np.array(boxes),
def preprocess(self, image):
if isinstance(image, np.ndarray):
processed = preprocess_tensor(
image, self.input_shape[1], self.input_shape[0]
)
)
return np.expand_dims(processed, axis=0)
else:
raise ValueError("Unsupported image format for preprocessing")
if combined.shape[0] < 20:
padding = np.zeros(
(20 - combined.shape[0], combined.shape[1]), dtype=combined.dtype
)
combined = np.vstack((combined, padding))
def close(self):
"""Properly shuts down the inference engine and releases the VDevice."""
logger.debug("[CLOSE] Closing HailoDetector")
try:
if hasattr(self, "inference_engine"):
if hasattr(self.inference_engine, "target"):
self.inference_engine.target.release()
logger.debug("Hailo VDevice released successfully")
except Exception as e:
logger.error(f"Failed to close Hailo device: {e}")
raise
logger.debug(
f"[process_detections] Combined detections (padded to 20 if necessary): {np.array_str(combined, precision=4, suppress_small=True)}"
)
def __del__(self):
"""Destructor to ensure cleanup when the object is deleted."""
self.close()
return combined[:20, :6]
# ----------------- HailoDetectorConfig Class ----------------- #
class HailoDetectorConfig(BaseDetectorConfig):
type: Literal[DETECTOR_KEY]
device: str = Field(default="PCIe", title="Device Type")