Error when starting a face detection job

[kachuan]

The bug

Hi,everyone. I have encountered an error when starting a face detection job . I have no idea whether is a bug or not.

I had deploy immich on ubuntu 22.04 （Vmware machine）with 2C4G . It all works well,but fails on my openwrt device.

• Immich Server Logs

[Nest] 8 - 02/09/2025, 11:32:44 PM WARN [Microservices:MachineLearningRepository] Machine learning request to "http://immich-machine-learning:3003" failed with status 500: Internal Server Error
[Nest] 8 - 02/09/2025, 11:32:44 PM ERROR [Microservices:JobService] Unable to run job handler (faceDetection/face-detection): Error: Machine learning request '{"facial-recognition":{"detection":{"modelName":"buffalo_l","options":{"minScore":0.7}},"recognition":{"modelName":"buffalo_l"}}}' failed for all URLs
[Nest] 8 - 02/09/2025, 11:32:44 PM ERROR [Microservices:JobService] Error: Machine learning request '{"facial-recognition":{"detection":{"modelName":"buffalo_l","options":{"minScore":0.7}},"recognition":{"modelName":"buffalo_l"}}}' failed for all URLs
at MachineLearningRepository.predict (/usr/src/app/dist/repositories/machine-learning.repository.js:38:15)
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async MachineLearningRepository.detectFaces (/usr/src/app/dist/repositories/machine-learning.repository.js:47:26)
at async PersonService.handleDetectFaces (/usr/src/app/dist/services/person.service.js:228:52)
at async JobService.onJobStart (/usr/src/app/dist/services/job.service.js:148:28)
at async EventRepository.onEvent (/usr/src/app/dist/repositories/event.repository.js:130:13)
at async Worker.processJob (/usr/src/app/node_modules/bullmq/dist/cjs/classes/worker.js:394:28)
at async Worker.retryIfFailed (/usr/src/app/node_modules/bullmq/dist/cjs/classes/worker.js:581:24)
[Nest] 8 - 02/09/2025, 11:32:44 PM ERROR [Microservices:JobService] Object:
{
"id": "c9064b8e-61c0-4cb6-935b-3aaa31cf237a"
}

• Immich Machine Learning Logs
  `[02/09/25 23:32:31] DEBUG Setting model format to onnx
  [02/09/25 23:32:31] INFO Loading detection model 'buffalo_l' to memory
  [02/09/25 23:32:31] DEBUG Available ORT providers: {'CPUExecutionProvider',
  'AzureExecutionProvider'}
  [02/09/25 23:32:31] INFO Setting execution providers to
  ['CPUExecutionProvider'], in descending order of
  preference
  [02/09/25 23:32:31] DEBUG Setting execution provider options to
  [{'arena_extend_strategy': 'kSameAsRequested'}]
  [02/09/25 23:32:31] DEBUG Setting execution_mode to ORT_SEQUENTIAL
  [02/09/25 23:32:31] DEBUG Setting inter_op_num_threads to 1
  [02/09/25 23:32:31] DEBUG Setting intra_op_num_threads to 2
  [02/09/25 23:32:37] DEBUG Checking for inactivity...
  [02/09/25 23:32:40] DEBUG Setting model format to onnx
  [02/09/25 23:32:40] INFO Loading recognition model 'buffalo_l' to memory
  [02/09/25 23:32:40] DEBUG Available ORT providers: {'CPUExecutionProvider',
  'AzureExecutionProvider'}
  [02/09/25 23:32:40] INFO Setting execution providers to
  ['CPUExecutionProvider'], in descending order of
  preference
  [02/09/25 23:32:40] DEBUG Setting execution provider options to
  [{'arena_extend_strategy': 'kSameAsRequested'}]
  [02/09/25 23:32:40] DEBUG Setting execution_mode to ORT_SEQUENTIAL
  [02/09/25 23:32:40] DEBUG Setting inter_op_num_threads to 1
  [02/09/25 23:32:40] DEBUG Setting intra_op_num_threads to 2
  [02/09/25 23:32:40] ERROR Exception in ASGI application

                         ╭─────── Traceback (most recent call last) ───────╮
                         │ /usr/src/app/main.py:177 in predict             │
                         │                                                 │
                         │   174 │   │   inputs = text                     │
                         │   175 │   else:                                 │
                         │   176 │   │   raise HTTPException(400, "Either  │
                         │ ❱ 177 │   response = await run_inference(inputs │
                         │   178 │   return ORJSONResponse(response)       │
                         │   179                                           │
                         │   180                                           │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ entries = (                                 │ │
                         │ │           │   [                             │ │
                         │ │           │   │   {                         │ │
                         │ │           │   │   │   'name': 'buffalo_l',  │ │
                         │ │           │   │   │   'task':               │ │
                         │ │           'facial-recognition',             │ │
                         │ │           │   │   │   'type': 'detection',  │ │
                         │ │           │   │   │   'options': {          │ │
                         │ │           │   │   │   │   'minScore': 0.7   │ │
                         │ │           │   │   │   }                     │ │
                         │ │           │   │   }                         │ │
                         │ │           │   ],                            │ │
                         │ │           │   [                             │ │
                         │ │           │   │   {                         │ │
                         │ │           │   │   │   'name': 'buffalo_l',  │ │
                         │ │           │   │   │   'task':               │ │
                         │ │           'facial-recognition',             │ │
                         │ │           │   │   │   'type':               │ │
                         │ │           'recognition',                    │ │
                         │ │           │   │   │   'options': {}         │ │
                         │ │           │   │   }                         │ │
                         │ │           │   ]                             │ │
                         │ │           )                                 │ │
                         │ │   image = b'\xff\xd8\xff\xe2\x01\xf0ICC_PR… │ │
                         │ │           \x00\x00mntrRGB XYZ               │ │
                         │ │           \x07\xe2\x00\x03\x00\x14\x00\t\x… │ │
                         │ │  inputs = <PIL.JpegImagePlugin.JpegImageFi… │ │
                         │ │           image mode=RGB size=1440x1920 at  │ │
                         │ │           0x7F606933D0>                     │ │
                         │ │    text = None                              │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/main.py:202 in run_inference       │
                         │                                                 │
                         │   199 │   without_deps, with_deps = entries     │
                         │   200 │   await asyncio.gather(*[_run_inference │
                         │   201 │   if with_deps:                         │
                         │ ❱ 202 │   │   await asyncio.gather(*[_run_infer │
                         │   203 │   if isinstance(payload, Image):        │
                         │   204 │   │   response["imageHeight"], response │
                         │   205                                           │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │      entries = (                            │ │
                         │ │                │   [                        │ │
                         │ │                │   │   {                    │ │
                         │ │                │   │   │   'name':          │ │
                         │ │                'buffalo_l',                 │ │
                         │ │                │   │   │   'task':          │ │
                         │ │                'facial-recognition',        │ │
                         │ │                │   │   │   'type':          │ │
                         │ │                'detection',                 │ │
                         │ │                │   │   │   'options': {     │ │
                         │ │                │   │   │   │   'minScore':  │ │
                         │ │                0.7                          │ │
                         │ │                │   │   │   }                │ │
                         │ │                │   │   }                    │ │
                         │ │                │   ],                       │ │
                         │ │                │   [                        │ │
                         │ │                │   │   {                    │ │
                         │ │                │   │   │   'name':          │ │
                         │ │                'buffalo_l',                 │ │
                         │ │                │   │   │   'task':          │ │
                         │ │                'facial-recognition',        │ │
                         │ │                │   │   │   'type':          │ │
                         │ │                'recognition',               │ │
                         │ │                │   │   │   'options': {}    │ │
                         │ │                │   │   }                    │ │
                         │ │                │   ]                        │ │
                         │ │                )                            │ │
                         │ │      outputs = {                            │ │
                         │ │                │   (<ModelType.DETECTION:   │ │
                         │ │                'detection'>,                │ │
                         │ │                <ModelTask.FACIAL_RECOGNITI… │ │
                         │ │                'facial-recognition'>): {    │ │
                         │ │                │   │   'boxes': array([],   │ │
                         │ │                shape=(0, 4),                │ │
                         │ │                dtype=float32),              │ │
                         │ │                │   │   'scores': array([],  │ │
                         │ │                dtype=float32),              │ │
                         │ │                │   │   'landmarks':         │ │
                         │ │                array([], shape=(0, 5, 2),   │ │
                         │ │                dtype=float32)               │ │
                         │ │                │   }                        │ │
                         │ │                }                            │ │
                         │ │      payload = <PIL.JpegImagePlugin.JpegIm… │ │
                         │ │                image mode=RGB               │ │
                         │ │                size=1440x1920 at            │ │
                         │ │                0x7F606933D0>                │ │
                         │ │     response = {                            │ │
                         │ │                │   'facial-recognition': {  │ │
                         │ │                │   │   'boxes': array([],   │ │
                         │ │                shape=(0, 4),                │ │
                         │ │                dtype=float32),              │ │
                         │ │                │   │   'scores': array([],  │ │
                         │ │                dtype=float32),              │ │
                         │ │                │   │   'landmarks':         │ │
                         │ │                array([], shape=(0, 5, 2),   │ │
                         │ │                dtype=float32)               │ │
                         │ │                │   }                        │ │
                         │ │                }                            │ │
                         │ │    with_deps = [                            │ │
                         │ │                │   {                        │ │
                         │ │                │   │   'name': 'buffalo_l', │ │
                         │ │                │   │   'task':              │ │
                         │ │                'facial-recognition',        │ │
                         │ │                │   │   'type':              │ │
                         │ │                'recognition',               │ │
                         │ │                │   │   'options': {}        │ │
                         │ │                │   }                        │ │
                         │ │                ]                            │ │
                         │ │ without_deps = [                            │ │
                         │ │                │   {                        │ │
                         │ │                │   │   'name': 'buffalo_l', │ │
                         │ │                │   │   'task':              │ │
                         │ │                'facial-recognition',        │ │
                         │ │                │   │   'type': 'detection', │ │
                         │ │                │   │   'options': {         │ │
                         │ │                │   │   │   'minScore': 0.7  │ │
                         │ │                │   │   }                    │ │
                         │ │                │   }                        │ │
                         │ │                ]                            │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/main.py:194 in _run_inference      │
                         │                                                 │
                         │   191 │   │   │   except KeyError:              │
                         │   192 │   │   │   │   message = f"Task {entry[' │
                         │       output of {dep}"                          │
                         │   193 │   │   │   │   raise HTTPException(400,  │
                         │ ❱ 194 │   │   model = await load(model)         │
                         │   195 │   │   output = await run(model.predict, │
                         │   196 │   │   outputs[model.identity] = output  │
                         │   197 │   │   response[entry["task"]] = output  │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │      dep = (                                │ │
                         │ │            │   <ModelType.DETECTION:        │ │
                         │ │            'detection'>,                    │ │
                         │ │            │                                │ │
                         │ │            <ModelTask.FACIAL_RECOGNITION:   │ │
                         │ │            'facial-recognition'>            │ │
                         │ │            )                                │ │
                         │ │    entry = {                                │ │
                         │ │            │   'name': 'buffalo_l',         │ │
                         │ │            │   'task':                      │ │
                         │ │            'facial-recognition',            │ │
                         │ │            │   'type': 'recognition',       │ │
                         │ │            │   'options': {}                │ │
                         │ │            }                                │ │
                         │ │   inputs = [                                │ │
                         │ │            │                                │ │
                         │ │            <PIL.JpegImagePlugin.JpegImageF… │ │
                         │ │            image mode=RGB size=1440x1920 at │ │
                         │ │            0x7F606933D0>,                   │ │
                         │ │            │   {                            │ │
                         │ │            │   │   'boxes': array([],       │ │
                         │ │            shape=(0, 4), dtype=float32),    │ │
                         │ │            │   │   'scores': array([],      │ │
                         │ │            dtype=float32),                  │ │
                         │ │            │   │   'landmarks': array([],   │ │
                         │ │            shape=(0, 5, 2), dtype=float32)  │ │
                         │ │            │   }                            │ │
                         │ │            ]                                │ │
                         │ │    model = <app.models.facial_recognition.… │ │
                         │ │            object at 0x7f60691810>          │ │
                         │ │  outputs = {                                │ │
                         │ │            │   (<ModelType.DETECTION:       │ │
                         │ │            'detection'>,                    │ │
                         │ │            <ModelTask.FACIAL_RECOGNITION:   │ │
                         │ │            'facial-recognition'>): {        │ │
                         │ │            │   │   'boxes': array([],       │ │
                         │ │            shape=(0, 4), dtype=float32),    │ │
                         │ │            │   │   'scores': array([],      │ │
                         │ │            dtype=float32),                  │ │
                         │ │            │   │   'landmarks': array([],   │ │
                         │ │            shape=(0, 5, 2), dtype=float32)  │ │
                         │ │            │   }                            │ │
                         │ │            }                                │ │
                         │ │  payload = <PIL.JpegImagePlugin.JpegImageF… │ │
                         │ │            image mode=RGB size=1440x1920 at │ │
                         │ │            0x7F606933D0>                    │ │
                         │ │ response = {                                │ │
                         │ │            │   'facial-recognition': {      │ │
                         │ │            │   │   'boxes': array([],       │ │
                         │ │            shape=(0, 4), dtype=float32),    │ │
                         │ │            │   │   'scores': array([],      │ │
                         │ │            dtype=float32),                  │ │
                         │ │            │   │   'landmarks': array([],   │ │
                         │ │            shape=(0, 5, 2), dtype=float32)  │ │
                         │ │            │   }                            │ │
                         │ │            }                                │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/main.py:238 in load                │
                         │                                                 │
                         │   235 │   │   return model                      │
                         │   236 │                                         │
                         │   237 │   try:                                  │
                         │ ❱ 238 │   │   return await run(_load, model)    │
                         │   239 │   except (OSError, InvalidProtobuf, Bad │
                         │   240 │   │   log.warning(f"Failed to load {mod │
                         │       '{model.model_name}'. Clearing cache.")   │
                         │   241 │   │   model.clear_cache()               │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ model = <app.models.facial_recognition.rec… │ │
                         │ │         object at 0x7f60691810>             │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/main.py:213 in run                 │
                         │                                                 │
                         │   210 │   if thread_pool is None:               │
                         │   211 │   │   return func(*args, **kwargs)      │
                         │   212 │   partial_func = partial(func, *args, * │
                         │ ❱ 213 │   return await asyncio.get_running_loop │
                         │   214                                           │
                         │   215                                           │
                         │   216 async def load(model: InferenceModel) ->  │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │         args = (                            │ │
                         │ │                │                            │ │
                         │ │                <app.models.facial_recognit… │ │
                         │ │                object at 0x7f60691810>,     │ │
                         │ │                )                            │ │
                         │ │       kwargs = {}                           │ │
                         │ │ partial_func = functools.partial(<function  │ │
                         │ │                load.<locals>._load at       │ │
                         │ │                0x7f6063bba0>,               │ │
                         │ │                <app.models.facial_recognit… │ │
                         │ │                object at 0x7f60691810>)     │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/local/lib/python3.11/concurrent/futures/th │
                         │ read.py:58 in run                               │
                         │                                                 │
                         │ /usr/src/app/main.py:225 in _load               │
                         │                                                 │
                         │   222 │   │   │   raise HTTPException(500, f"Fa │
                         │   223 │   │   with lock:                        │
                         │   224 │   │   │   try:                          │
                         │ ❱ 225 │   │   │   │   model.load()              │
                         │   226 │   │   │   except FileNotFoundError as e │
                         │   227 │   │   │   │   if model.model_format ==  │
                         │   228 │   │   │   │   │   raise e               │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ model = <app.models.facial_recognition.rec… │ │
                         │ │         object at 0x7f60691810>             │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/models/base.py:53 in load          │
                         │                                                 │
                         │    50 │   │   self.download()                   │
                         │    51 │   │   attempt = f"Attempt #{self.load_a │
                         │       else "Loading"                            │
                         │    52 │   │   log.info(f"{attempt} {self.model_ │
                         │       '{self.model_name}' to memory")           │
                         │ ❱  53 │   │   self.session = self._load()       │
                         │    54 │   │   self.loaded = True                │
                         │    55 │                                         │
                         │    56 │   def predict(self, *inputs: Any, **mod │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ attempt = 'Loading'                         │ │
                         │ │    self = <app.models.facial_recognition.r… │ │
                         │ │           object at 0x7f60691810>           │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/models/facial_recognition/recognit │
                         │ ion.py:30 in _load                              │
                         │                                                 │
                         │   27 │   │   self.batch_size = max_batch_size i │
                         │   28 │                                          │
                         │   29 │   def _load(self) -> ModelSession:       │
                         │ ❱ 30 │   │   session = self._make_session(self. │
                         │   31 │   │   if (not self.batch_size or self.ba │
                         │      str(session.get_inputs()[0].shape[0]) != " │
                         │   32 │   │   │   self._add_batch_axis(self.mode │
                         │   33 │   │   │   session = self._make_session(s │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ self = <app.models.facial_recognition.reco… │ │
                         │ │        object at 0x7f60691810>              │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/models/base.py:110 in              │
                         │ _make_session                                   │
                         │                                                 │
                         │   107 │   │   │   case ".armnn":                │
                         │   108 │   │   │   │   session: ModelSession = A │
                         │   109 │   │   │   case ".onnx":                 │
                         │ ❱ 110 │   │   │   │   session = OrtSession(mode │
                         │   111 │   │   │   case _:                       │
                         │   112 │   │   │   │   raise ValueError(f"Unsupp │
                         │   113 │   │   return session                    │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ model_path = PosixPath('/cache/facial-reco… │ │
                         │ │       self = <app.models.facial_recognitio… │ │
                         │ │              object at 0x7f60691810>        │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /usr/src/app/sessions/ort.py:28 in __init__     │
                         │                                                 │
                         │    25 │   │   self.providers = providers if pro │
                         │    26 │   │   self.provider_options = provider_ │
                         │       self._provider_options_default            │
                         │    27 │   │   self.sess_options = sess_options  │
                         │       self._sess_options_default                │
                         │ ❱  28 │   │   self.session = ort.InferenceSessi │
                         │    29 │   │   │   self.model_path.as_posix(),   │
                         │    30 │   │   │   providers=self.providers,     │
                         │    31 │   │   │   provider_options=self.provide │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │       model_path = PosixPath('/cache/facia… │ │
                         │ │ provider_options = None                     │ │
                         │ │        providers = None                     │ │
                         │ │             self = <app.sessions.ort.OrtSe… │ │
                         │ │                    object at 0x7f609233d0>  │ │
                         │ │     sess_options = None                     │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /opt/venv/lib/python3.11/site-packages/onnxrunt │
                         │ ime/capi/onnxruntime_inference_collection.py:46 │
                         │ 5 in __init__                                   │
                         │                                                 │
                         │    462 │   │   disabled_optimizers = kwargs.get │
                         │    463 │   │                                    │
                         │    464 │   │   try:                             │
                         │ ❱  465 │   │   │   self._create_inference_sessi │
                         │        disabled_optimizers)                     │
                         │    466 │   │   except (ValueError, RuntimeError │
                         │    467 │   │   │   if self._enable_fallback:    │
                         │    468 │   │   │   │   try:                     │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ disabled_optimizers = None                  │ │
                         │ │              kwargs = {}                    │ │
                         │ │       path_or_bytes = '/cache/facial-recog… │ │
                         │ │    provider_options = [                     │ │
                         │ │                       │   {                 │ │
                         │ │                       │   │                 │ │
                         │ │                       'arena_extend_strate… │ │
                         │ │                       'kSameAsRequested'    │ │
                         │ │                       │   }                 │ │
                         │ │                       ]                     │ │
                         │ │           providers = [                     │ │
                         │ │                       │                     │ │
                         │ │                       'CPUExecutionProvide… │ │
                         │ │                       ]                     │ │
                         │ │                self = <onnxruntime.capi.on… │ │
                         │ │                       object at             │ │
                         │ │                       0x7f60d49210>         │ │
                         │ │        sess_options = <onnxruntime.capi.on… │ │
                         │ │                       object at             │ │
                         │ │                       0x7f609ff0b0>         │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         │                                                 │
                         │ /opt/venv/lib/python3.11/site-packages/onnxrunt │
                         │ ime/capi/onnxruntime_inference_collection.py:52 │
                         │ 6 in _create_inference_session                  │
                         │                                                 │
                         │    523 │   │   self._register_ep_custom_ops(ses │
                         │        available_providers)                     │
                         │    524 │   │                                    │
                         │    525 │   │   if self._model_path:             │
                         │ ❱  526 │   │   │   sess = C.InferenceSession(se │
                         │        self._read_config_from_model)            │
                         │    527 │   │   else:                            │
                         │    528 │   │   │   sess = C.InferenceSession(se │
                         │        self._read_config_from_model)            │
                         │    529                                          │
                         │                                                 │
                         │ ╭────────────────── locals ───────────────────╮ │
                         │ │ available_providers = [                     │ │
                         │ │                       │                     │ │
                         │ │                       'AzureExecutionProvi… │ │
                         │ │                       │                     │ │
                         │ │                       'CPUExecutionProvide… │ │
                         │ │                       ]                     │ │
                         │ │ disabled_optimizers = None                  │ │
                         │ │    provider_options = [                     │ │
                         │ │                       │   {                 │ │
                         │ │                       │   │                 │ │
                         │ │                       'arena_extend_strate… │ │
                         │ │                       'kSameAsRequested'    │ │
                         │ │                       │   }                 │ │
                         │ │                       ]                     │ │
                         │ │           providers = [                     │ │
                         │ │                       │                     │ │
                         │ │                       'CPUExecutionProvide… │ │
                         │ │                       ]                     │ │
                         │ │                self = <onnxruntime.capi.on… │ │
                         │ │                       object at             │ │
                         │ │                       0x7f60d49210>         │ │
                         │ │     session_options = <onnxruntime.capi.on… │ │
                         │ │                       object at             │ │
                         │ │                       0x7f609ff0b0>         │ │
                         │ ╰─────────────────────────────────────────────╯ │
                         ╰─────────────────────────────────────────────────╯
                         Fail: [ONNXRuntimeError] : 1 : FAIL : Load model
                         from
                         /cache/facial-recognition/buffalo_l/recognition/mod
                         el.onnx
                         failed:/onnxruntime_src/onnxruntime/core/graph/mode
                         l.cc:165
                         onnxruntime::Model::Model(onnx::ModelProto&&, const
                         onnxruntime::PathString&, const
                         onnxruntime::IOnnxRuntimeOpSchemaRegistryList*,
                         const onnxruntime::logging::Logger&, const
                         onnxruntime::ModelOptions&) ModelProto does not
                         have a graph.
  

[02/09/25 23:32:43] INFO Attempt #2 to load recognition model 'buffalo_l' to
memory
[02/09/25 23:32:43] DEBUG Available ORT providers: {'CPUExecutionProvider',
'AzureExecutionProvider'}
[02/09/25 23:32:43] INFO Setting execution providers to
['CPUExecutionProvider'], in descending order of
preference
[02/09/25 23:32:43] DEBUG Setting execution provider options to
[{'arena_extend_strategy': 'kSameAsRequested'}]
[02/09/25 23:32:43] DEBUG Setting execution_mode to ORT_SEQUENTIAL
[02/09/25 23:32:43] DEBUG Setting inter_op_num_threads to 1
[02/09/25 23:32:43] DEBUG Setting intra_op_num_threads to 2
`

• OpenWrt Hardware
  Phicomm N1
  SoC：Allogic S905D 64bit 4Core Cortex-A53 1.5G Hz
  GPU：Mali-450
  RAM：2GB + 8GB Swap
  ROM：8GB eMMC

The OS that Immich Server is running on

Linux OpenWrt

Version of Immich Server

v1.125.7

Version of Immich Mobile App

v1.125.3

Platform with the issue

• Server
• Web
• Mobile

Your docker-compose.yml content

#
# WARNING: Make sure to use the docker-compose.yml of the current release:
#
# https://github.com/immich-app/immich/releases/latest/download/docker-compose.yml
#
# The compose file on main may not be compatible with the latest release.
#

name: immich

services:
  immich-server:
    container_name: immich_server
    image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
    # extends:
    #   file: hwaccel.transcoding.yml
    #   service: cpu # set to one of [nvenc, quicksync, rkmpp, vaapi, vaapi-wsl] for accelerated transcoding
    volumes:
      # Do not edit the next line. If you want to change the media storage location on your system, edit the value of UPLOAD_LOCATION in the .env file
      - ${UPLOAD_LOCATION}:/usr/src/app/upload
      - /etc/localtime:/etc/localtime:ro
    env_file:
      - .env
    ports:
      - '2283:2283'
    depends_on:
      - redis
      - database
    restart: always
    healthcheck:
      disable: false

  immich-machine-learning:
    container_name: immich_machine_learning
    # For hardware acceleration, add one of -[armnn, cuda, openvino] to the image tag.
    # Example tag: ${IMMICH_VERSION:-release}-cuda
    image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}
    # extends: # uncomment this section for hardware acceleration - see https://immich.app/docs/features/ml-hardware-acceleration
    #   file: hwaccel.ml.yml
    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference - use the `-wsl` version for WSL2 where applicable
    volumes:
      - model-cache:/cache
    env_file:
      - .env
    restart: always
    healthcheck:
      disable: false

  redis:
    container_name: immich_redis
    image: docker.io/redis:6.2-alpine@sha256:905c4ee67b8e0aa955331960d2aa745781e6bd89afc44a8584bfd13bc890f0ae
    healthcheck:
      test: redis-cli ping || exit 1
    restart: always
    environment:
      TZ: Asia/Shanghai
  database:
    container_name: immich_postgres
    image: docker.io/tensorchord/pgvecto-rs:pg14-v0.2.0@sha256:90724186f0a3517cf6914295b5ab410db9ce23190a2d9d0b9dd6463e3fa298f0
    environment:
      TZ: Asia/Shanghai
      POSTGRES_PASSWORD: ${DB_PASSWORD}
      POSTGRES_USER: ${DB_USERNAME}
      POSTGRES_DB: ${DB_DATABASE_NAME}
      POSTGRES_INITDB_ARGS: '--data-checksums'
    volumes:
      # Do not edit the next line. If you want to change the database storage location on your system, edit the value of DB_DATA_LOCATION in the .env file
      - ${DB_DATA_LOCATION}:/var/lib/postgresql/data
    healthcheck:
      test: >-
        pg_isready --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" || exit 1;
        Chksum="$$(psql --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" --tuples-only --no-align
        --command='SELECT COALESCE(SUM(checksum_failures), 0) FROM pg_stat_database')";
        echo "checksum failure count is $$Chksum";
        [ "$$Chksum" = '0' ] || exit 1
      interval: 5m
      start_interval: 30s
      start_period: 5m
    command: >-
      postgres
      -c shared_preload_libraries=vectors.so
      -c 'search_path="$$user", public, vectors'
      -c logging_collector=on
      -c max_wal_size=2GB
      -c shared_buffers=512MB
      -c wal_compression=on
    restart: always

volumes:
  model-cache:

Your .env content

# You can find documentation for all the supported env variables at https://immich.app/docs/install/environment-variables

# The location where your uploaded files are stored
UPLOAD_LOCATION=./library
# The location where your database files are stored
DB_DATA_LOCATION=./data/postgres

# To set a timezone, uncomment the next line and change Etc/UTC to a TZ identifier from this list: https://en.wikipedia.org/wiki/List_of_tz_database_time_zones#List
# TZ=Etc/UTC
TZ=Asia/Shanghai
CPU_CORES=2

# The Immich version to use. You can pin this to a specific version like "v1.71.0"
IMMICH_VERSION=v1.125.7

# Connection secret for postgres. You should change it to a random password
# Please use only the characters `A-Za-z0-9`, without special characters or spaces
DB_PASSWORD=postgres

# The values below this line do not need to be changed
###################################################################################
DB_USERNAME=postgres
DB_DATABASE_NAME=immich

IMMICH_LOG_LEVEL=debug

Reproduction steps

...

Relevant log output

Additional information

No response

[bo0tzz]

Do I understand right that you're trying to run Immich on a piece of low-power networking hardware? That probably doesn't have enough resources to run Immich properly.

[kachuan]

Do I understand right that you're trying to run Immich on a piece of low-power networking hardware? That probably doesn't have enough resources to run Immich properly.

Yeah,it is lower-powered. Actually, i don't need a high pefermance device.It's slow when uploading my photos at first time,but faster for daily-updated photos.It's ok that I can look up my photos on immich in hours.It will be fancy if it can handle face detection.
Now the problem is caused by cpu or memory limit, right?

[bo0tzz]

Yes, I'm pretty sure the system is just not able to cope with what you're asking of it. Try disabling ML or running it remotely.