mirror of
https://github.com/blakeblackshear/frigate.git
synced 2025-08-04 13:47:37 +02:00
Version that detects model and can begin using @local
This commit is contained in:
Chirayu Rai
parent
52a9bdf2b9
commit
4412671e76
@ -26,16 +26,24 @@ services:
|
||||
YOLO_MODELS: ""
|
||||
devices:
|
||||
- /dev/bus/usb:/dev/bus/usb
|
||||
# - /dev/dri:/dev/dri # for intel hwaccel, needs to be updated for your hardware
|
||||
- /dev/dri:/dev/dri # for intel hwaccel, needs to be updated for your hardware
|
||||
volumes:
|
||||
- .:/workspace/frigate:cached
|
||||
- ./web/dist:/opt/frigate/web:cached
|
||||
- /etc/localtime:/etc/localtime:ro
|
||||
- ./config:/config
|
||||
- ./debug:/media/frigate
|
||||
- /dev/bus/usb:/dev/bus/usb
|
||||
- ./model:/zoo
|
||||
- ./test_short.mp4:/testing/test_short.mp4
|
||||
mqtt:
|
||||
container_name: mqtt
|
||||
image: eclipse-mosquitto:1.6
|
||||
ports:
|
||||
- "1883:1883"
|
||||
- "1883:1883"
|
||||
degirum_detector:
|
||||
container_name: degirum
|
||||
image: degirum/aiserver:latest
|
||||
privileged: true
|
||||
ports:
|
||||
- "8778:8778"
|
||||
|
||||
|
||||
@ -72,4 +72,5 @@ prometheus-client == 0.21.*
|
||||
tflite_runtime @ https://github.com/frigate-nvr/TFlite-builds/releases/download/v2.17.1/tflite_runtime-2.17.1-cp311-cp311-linux_x86_64.whl; platform_machine == 'x86_64'
|
||||
tflite_runtime @ https://github.com/feranick/TFlite-builds/releases/download/v2.17.1/tflite_runtime-2.17.1-cp311-cp311-linux_aarch64.whl; platform_machine == 'aarch64'
|
||||
# DeGirum detector
|
||||
degirum_headless == 0.15.*
|
||||
degirum == 0.16.*
|
||||
# degirum_headless == 0.15.*
|
||||
|
||||
@ -87,43 +87,135 @@ class DGDetector(DetectionApi):
|
||||
self._zoo = dg.connect(
|
||||
detector_config.location, detector_config.zoo, detector_config.token
|
||||
)
|
||||
logger.info(f"Models in zoo: {self._zoo.list_models()}")
|
||||
self.dg_model = self._zoo.load_model(
|
||||
detector_config.model.path, non_blocking_batch_predict=True
|
||||
detector_config.model.path,
|
||||
)
|
||||
self.dg_model.measure_time = True
|
||||
self.dg_model.input_image_format = "RAW"
|
||||
self.dg_model._postprocessor = None
|
||||
# Openvino tends to have multidevice, and they default to CPU rather than GPU or NPU
|
||||
types = self.dg_model.supported_device_types
|
||||
for type in types:
|
||||
# If openvino is supported, prioritize using gpu, then npu, then cpu
|
||||
if "OPENVINO" in type:
|
||||
self.dg_model.device_type = [
|
||||
"OPENVINO/GPU",
|
||||
"OPENVINO/NPU",
|
||||
# "OPENVINO/GPU",
|
||||
# "OPENVINO/NPU",
|
||||
"OPENVINO/CPU",
|
||||
]
|
||||
elif "HAILORT" in type:
|
||||
self.dg_model.device_type = [
|
||||
"HAILORT/HAILO8l",
|
||||
"HAILORT/HAILO8",
|
||||
]
|
||||
break
|
||||
self.model_height = detector_config.model.height
|
||||
self.model_width = detector_config.model.width
|
||||
self.predict_batch = self.dg_model.predict_batch(self._queue)
|
||||
input_shape = self.dg_model.input_shape[0]
|
||||
self.model_height = input_shape[1]
|
||||
self.model_width = input_shape[2]
|
||||
|
||||
frame = np.zeros(
|
||||
(detector_config.model.width, detector_config.model.height, 3),
|
||||
dtype=np.uint8,
|
||||
)
|
||||
self.dg_model(frame)
|
||||
self.prediction = self.prediction_generator()
|
||||
self.none_counter = 0
|
||||
self.not_none_counter = 0
|
||||
self.overall_frame_counter = 0
|
||||
self.times = 0
|
||||
|
||||
def prediction_generator(self):
|
||||
# logger.debug("Prediction generator was called")
|
||||
with self.dg_model as model:
|
||||
while 1:
|
||||
# logger.debug(f"q size before calling get: {self._queue.qsize()}")
|
||||
data = self._queue.get()
|
||||
# logger.debug(f"q size after calling get: {self._queue.qsize()}")
|
||||
# logger.debug(
|
||||
# f"Data we're passing into model predict: {data}, shape of data: {data.shape}"
|
||||
# )
|
||||
start = time.time_ns()
|
||||
result = model.predict(data)
|
||||
self.times += (time.time_ns() - start) * 1e-6
|
||||
# logger.info(
|
||||
# f"Entire time taken to get result back: {self.times / self.overall_frame_counter}"
|
||||
# )
|
||||
yield result
|
||||
|
||||
def detect_raw(self, tensor_input):
|
||||
# add tensor_input to input queue
|
||||
# start = time.time_ns()
|
||||
self.overall_frame_counter += 1
|
||||
truncated_input = tensor_input.reshape(tensor_input.shape[1:])
|
||||
self._queue.put((truncated_input, ""))
|
||||
# logger.debug(f"Detect raw was called for tensor input: {tensor_input}")
|
||||
|
||||
# add tensor_input to input queue
|
||||
self._queue.put(truncated_input)
|
||||
# logger.debug(f"Queue size after adding truncated input: {self._queue.qsize()}")
|
||||
|
||||
# define empty detection result
|
||||
detections = np.zeros((20, 6), np.float32)
|
||||
res = next(self.predict_batch)
|
||||
if res is not None:
|
||||
# res = next(self.prediction)
|
||||
result = next(self.prediction)
|
||||
# return detections
|
||||
# result = self.prediction_generator()
|
||||
# logger.info(f"Result: {result}")
|
||||
# logger.info(f"Shape of res: {res.results[0]["data"]}")
|
||||
# logger.debug(f"Queue size after calling for res: {self._queue.qsize()}")
|
||||
# logger.debug(f"Output of res in initial next call: {res}")
|
||||
# logger.info(
|
||||
# f"Overall frame number: {self.overall_frame_counter}, none count: {self.none_counter}, not none count: {self.not_none_counter}, none percentage: {self.none_counter / self.overall_frame_counter}"
|
||||
# )
|
||||
# logger.info(f"Time stats right after res: {self.dg_model.time_stats()}")
|
||||
# start = time.time_ns()
|
||||
|
||||
# res_string = str(res)
|
||||
# logger.info(f"Res is: {res_string}")
|
||||
# logger.debug(f"Res's list of attributes: {dir(res)}")
|
||||
# logger.debug(
|
||||
# f"Res results, {res.results}, length of results: {len(res.results)}"
|
||||
# )
|
||||
# logger.info(f"Output of res: {res}")
|
||||
# res_string = str(res)
|
||||
# logger.info(f"Data from array: {res.results}")
|
||||
# logger.info(f"First data: {res.results[0]['data']}")
|
||||
# logger.info(f"Length of data: {len(res.results[0]['data'][0])}")
|
||||
# if res is not None and res.results[0].get("category_id") is not None:
|
||||
if result is not None:
|
||||
# populate detection result with corresponding inference result information
|
||||
# self.not_none_counter += 1
|
||||
i = 0
|
||||
for result in res.results:
|
||||
detections[i] = [
|
||||
result["category_id"], # Label ID
|
||||
float(result["score"]), # Confidence
|
||||
result["bbox"][1] / self.model_height, # y_min
|
||||
result["bbox"][0] / self.model_width, # x_min
|
||||
result["bbox"][3] / self.model_height, # y_max
|
||||
result["bbox"][2] / self.model_width, # x_max
|
||||
]
|
||||
|
||||
# for result in res.results:
|
||||
# if i > 20:
|
||||
# break
|
||||
|
||||
# detections[i] = [
|
||||
# result["category_id"],
|
||||
# float(result["score"]),
|
||||
# result["bbox"][1] / self.model_height,
|
||||
# result["bbox"][0] / self.model_width,
|
||||
# result["bbox"][3] / self.model_height,
|
||||
# result["bbox"][2] / self.model_width,
|
||||
# ]
|
||||
# i += 1
|
||||
|
||||
for item in result.results:
|
||||
# logger.info(f"CURRENT ITEM: {item}")
|
||||
if i >= 20:
|
||||
break
|
||||
|
||||
category_id = int(item[5])
|
||||
score = item[4]
|
||||
y_min = item[1]
|
||||
x_min = item[0]
|
||||
x_max = item[2]
|
||||
y_max = item[3]
|
||||
detections[i] = [category_id, score, y_min, x_min, y_max, x_max]
|
||||
i += 1
|
||||
|
||||
if detections[0][1] != 0: # if we have a score, then print detection
|
||||
logger.info(f"Output of detections: {detections}")
|
||||
## Save the detection results to a file so we can compare
|
||||
# logger.info(f"Overall time took: {(time.time_ns() - start) * 1e-6}ms")
|
||||
return detections
|
||||
|
||||
95
model/ssdlite_mobilenet_v2--openvino1/labels.json
Normal file
95
model/ssdlite_mobilenet_v2--openvino1/labels.json
Normal file
@ -0,0 +1,95 @@
|
||||
{
|
||||
"0": "__background__",
|
||||
"1": "person",
|
||||
"2": "bicycle",
|
||||
"3": "car",
|
||||
"4": "motorcycle",
|
||||
"5": "airplan",
|
||||
"6": "bus",
|
||||
"7": "train",
|
||||
"8": "car",
|
||||
"9": "boat",
|
||||
"10": "traffic light",
|
||||
"11": "fire hydrant",
|
||||
"12": "street sign",
|
||||
"13": "stop sign",
|
||||
"14": "parking meter",
|
||||
"15": "bench",
|
||||
"16": "bird",
|
||||
"17": "cat",
|
||||
"18": "dog",
|
||||
"19": "horse",
|
||||
"20": "sheep",
|
||||
"21": "cow",
|
||||
"22": "elephant",
|
||||
"23": "bear",
|
||||
"24": "zebra",
|
||||
"25": "giraffe",
|
||||
"26": "hat",
|
||||
"27": "backpack",
|
||||
"28": "umbrella",
|
||||
"29": "shoe",
|
||||
"30": "eye glasses",
|
||||
"31": "handbag",
|
||||
"32": "tie",
|
||||
"33": "suitcase",
|
||||
"34": "frisbee",
|
||||
"35": "skis",
|
||||
"36": "snowboard",
|
||||
"37": "sports ball",
|
||||
"38": "kite",
|
||||
"39": "baseball bat",
|
||||
"40": "baseball glove",
|
||||
"41": "skateboard",
|
||||
"42": "surfboard",
|
||||
"43": "tennis racket",
|
||||
"44": "bottle",
|
||||
"45": "plate",
|
||||
"46": "wine glass",
|
||||
"47": "cup",
|
||||
"48": "fork",
|
||||
"49": "knife",
|
||||
"50": "spoon",
|
||||
"51": "bowl",
|
||||
"52": "banana",
|
||||
"53": "apple",
|
||||
"54": "sandwich",
|
||||
"55": "orange",
|
||||
"56": "broccoli",
|
||||
"57": "carrot",
|
||||
"58": "hot dog",
|
||||
"59": "pizza",
|
||||
"60": "donut",
|
||||
"61": "cake",
|
||||
"62": "chair",
|
||||
"63": "couch",
|
||||
"64": "potted plant",
|
||||
"65": "bed",
|
||||
"66": "mirror",
|
||||
"67": "dining table",
|
||||
"68": "window",
|
||||
"69": "desk",
|
||||
"70": "toilet",
|
||||
"71": "door",
|
||||
"72": "tv",
|
||||
"73": "laptop",
|
||||
"74": "mouse",
|
||||
"75": "remote",
|
||||
"76": "keyboard",
|
||||
"77": "cell phone",
|
||||
"78": "microwave",
|
||||
"79": "oven",
|
||||
"80": "toaster",
|
||||
"81": "sink",
|
||||
"82": "refrigerator",
|
||||
"83": "blender",
|
||||
"84": "book",
|
||||
"85": "clock",
|
||||
"86": "vase",
|
||||
"87": "scissors",
|
||||
"88": "teddy bear",
|
||||
"89": "hair drier",
|
||||
"90": "toothbrush",
|
||||
"91": "hair brush"
|
||||
}
|
||||
|
||||
Binary file not shown.
@ -0,0 +1,53 @@
|
||||
{
|
||||
"ConfigVersion": 6,
|
||||
"Checksum": "0ebce8b115214756bd37cfb5b4c3b547d557c6c58e828a8b9f725214afe49600",
|
||||
"DEVICE": [
|
||||
{
|
||||
"RuntimeAgent": "OPENVINO",
|
||||
"DeviceType": "CPU",
|
||||
"SupportedDeviceTypes": "OPENVINO/CPU"
|
||||
}
|
||||
],
|
||||
"MODEL_PARAMETERS": [
|
||||
{
|
||||
"ModelPath": "ssdlite_mobilenet_v2.xml"
|
||||
}
|
||||
],
|
||||
"PRE_PROCESS": [
|
||||
{
|
||||
"InputImgFmt": "JPEG",
|
||||
"InputImgNormEn": false,
|
||||
"InputN": 1,
|
||||
"InputType": "Image",
|
||||
"InputResizeMethod": "bilinear",
|
||||
"InputPadMethod": "letterbox",
|
||||
"ImageBackend": "auto",
|
||||
"InputH": 300,
|
||||
"InputW": 300,
|
||||
"InputC": 3,
|
||||
"InputQuantEn": true,
|
||||
"InputQuantOffset": 0,
|
||||
"InputQuantScale": 1,
|
||||
"InputTensorLayout": "NCHW",
|
||||
"InputImgSliceType": "None"
|
||||
}
|
||||
],
|
||||
"POST_PROCESS": [
|
||||
{
|
||||
"PostProcessorInputs": [3, 1, 2],
|
||||
"OutputPostprocessType": "Detection",
|
||||
"LabelsPath": "labels.json",
|
||||
"OutputConfThreshold": 0.3,
|
||||
"MaxDetections": 20,
|
||||
"OutputNMSThreshold": 0.6,
|
||||
"MaxDetectionsPerClass": 100,
|
||||
"MaxClassesPerDetection": 1,
|
||||
"UseRegularNMS": false,
|
||||
"OutputNumClasses": 90,
|
||||
"XScale": 10,
|
||||
"YScale": 10,
|
||||
"HScale": 5,
|
||||
"WScale": 5
|
||||
}
|
||||
]
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user