12 Commits

Include renames

Author	SHA1	Message	Date
4 people	91e91c68ef	Add Axelera Metis NPU detector plugin v.0.19 (#24270) ... * Add Axelera Metis NPU object detector plugin Runs Frigate inference on the Axelera Metis NPU through the vendor's low-level axelera.runtime API with pip-installed, sha256-pinned wheels from Axelera's public artifactory (self-contained: auditwheel-repaired libs + bundled firmware). - async send_input/receive_output contract (FIFO pairing, overload emits zero rows instead of raising, frames are copied out of camera shm) - generic YOLO-family decoder driven by the compiled model's manifest.json (padded input geometry, dequant params, baked postprocess graph via onnx) - labels come from the compiled model's model_info.json; empty labelmaps fail loudly at init * object_detection: async runner path for the axelera detector * detectors: detect_axelera probe (/dev/metis*) + device node init * stats: Axelera Metis board temperature poller The card exposes no utilization counter usable next to a live detector, so the poller reports the board-controller temperature read via axcmd (cached 5s; the read must not race detector init). * docs: Axelera Metis detector (install, config, model catalog, downloads) * axelera: expose Metis colon-name device node and image deps for runtime enumeration The Axelera runtime enumerates Metis cards via the colon-separated node name created by the vendor udev rule on the host (e.g. /dev/metis-0:1:0) and probes kernel state with lsmod/lspci. Containers only receive the raw /dev/metis-0-1-0 node, so the detector never found the card. - init-devices: create /dev/metis-BB:DD:F aliases for each Metis node - install_deps: add kmod and pciutils so the runtime's driver check works * axelera: review round 2 (downloader, stop release, pixel format, docs size, per-class NMS) - download model zips through ModelDownloader (atomic .part rename; a truncated download no longer poisons the cache) - stop(): release the Context (releases connection/model/instance); the previous instance.free() call never existed in the runtime API and was silently swallowed - honor input_pixel_format: flip to RGB planes only when Frigate delivers BGR (input_pixel_format: bgr); with rgb the frame passes through as-is - docs/catalog: width/height = compiled 640x640 input (square regions no longer get squashed twice), document input_pixel_format: bgr - NMS via xyxy_to_xywh_for_nms + per-class cv2.dnn.NMSBoxes, matching the other detector plugins instead of a hand-rolled class-agnostic pass * axelera: report Metis temperature only on the NPU card The same board readout was surfaced twice on the System page: once as the detector temperature (get_hardware_temperatures) and once on the NPU card (npu_usages). Keep the NPU card, where the value belongs. * axelera: report AIPU utilization as the detector run duty cycle The runtime exposes no device-side usage counter (mvm_utilisation is a configuration limit, not a readout), so the NPU card rendered empty. ModelInstance.run blocks until the AIPU completes: the detector process now times each run and publishes busy/wall over a 2s window through a small file under the tmp cache dir; the stats poller reads it and sets the npu key. A stale file (detector idle/restarting) reports nothing rather than a stale number. * axelera: cut hot-path allocations in preprocess and dequantise Preprocess reused three fresh arrays per frame (resize output, quantised copy, strided channel flip at write time) and refilled the whole padded input buffer. Now resize writes into a scratch with cv2 dst=, the BGR->RGB swap is a cvtColor into scratch (no strided copy), the int8 quantise runs with out=, and only the border strips the content rect does not cover get memset. Measured 39% faster on the 704x576 -> 640x640 path. Dequantise allocated two fp32 temporaries per head (astype then the dequant expression) before the transpose copy. copyto now casts int8->fp32 while transposing straight into a reused fp32 feed buffer, and the zp/scale math runs in place. Measured 78% faster for the YOLOX-S head set, outputs bit-identical (int8->fp32 cast is lossless). Argmax+gather replaces max+argmax (one class-axis reduction instead of two), and the postprocess session pins intra_op_num_threads=1: one frame is in flight through the decoder, extra ORT threads only add context switches. * axelera: publish the run duty cycle through a shared Value Replace the tmp-file duty-cycle handoff (and the FRIGATE_TMP env var nothing else reads) with a third multiprocessing.Value alongside avg_inference_speed and detection_start: ObjectDetectProcess creates it, AsyncDetectorRunner passes it to the detector, and the plugin publishes busy/wall of the blocking ModelInstance.run over a 2s window, mirroring how memryx receives its shared state. No filesystem path, no staleness window, no atomic rename, and stats/hardware.py no longer imports the plugin module to find the file. The producer also ticks the window while the queue is empty, so the duty cycle falls to 0 when the card idles instead of sticking at its last value. Name it what it is: host-side occupancy of the run call, including DMA and driver time, not an AIPU core counter (the runtime exposes no device-side one). The NPU entry now reads temperature from the board controller plus the detector-reported run duty cycle folded in where the detector processes are in reach. * axelera: enumerate devices explicitly and fail with an actionable error Context.list_devices() keys off the lspci BDF and needs the colon-form node to be present, so surface an empty enumeration at init with the fix-it hint instead of a bare device_connect(None) ConnectionError several frames deeper. Uses the DeviceInfo the runtime enumerated rather than relying on the pick-first implicit path. * axelera: deliver every accepted result under backpressure, reset duty cycle on restart Greptile P1: _push_result dropped a completion when the result queue was full, stranding the runner's send_times entry and the input SHM mapping (1 submission : 1 result contract). Replace the drop with a stop-aware blocking put so an accepted submission always produces exactly one delivered completion. Greptile P2: start_or_restart did not clear run_duty_cycle when starting a replacement process, so stats could show the previous process's duty cycle while the new detector was still initializing. Reset it to the -1.0 sentinel alongside detection_start, inside the async branch. Greptile P2 (offline docs): list axelera among the detector types whose pre-seeded runtime files live under /config/model_cache/runtimes/<type>. * axelera: reviewer round 3 (plugin-owned enumeration tools, generic DEVICE_ALIASES, generic duty-cycle fold) install_deps.sh: drop kmod/pciutils from the base image. The runtime's list_devices() only greps popen'd lspci/lsmod output over /sys and /proc, so the plugin now installs shell stand-ins in its own /config/model_cache/axelera/bin and prepends it to PATH when the real tools are missing (hardware-verified: the stand-in lspci prints the Device 1f9d:<id> line the runtime matches, the lsmod shape matches /proc/modules). init-devices: replace the Metis-keyed alias block with a generic DEVICE_ALIASES env var (comma separated alias=target pairs, next to DEVICE_ACL_PATHS). Docker rejects colon-named nodes in --device AND in bind mounts (probed: 'too many colons' on both the long volume form and the mount form), so the in-container symlink stays necessary; docs carry the pair users must set. stats/util.py: fold any detector's published run_duty_cycle into the matching npu_usages entry generically; _axelera_run_duty_cycle and the per-vendor branch are gone. plugin: the no-device RuntimeError now names the raw dash-form node (--device rejects colons, users can only pass the raw node) and points at DEVICE_ALIASES for the colon alias. * axelera: reviewer round 4 (aggregate shared-type duty cycles, american spellings) stats/util.py: several detector processes can share one hardware type (e.g. two axelera cards on one host). Iterating and assigning made the displayed NPU usage depend on dict order, last writer wins. Collect the published windows per type and write the busiest one, matching what the removed per-vendor helper did with max(). plugin: the remaining British spellings (dequantise family) corrected to the American forms the repo requires. plugin: model path resolution follows hailo8l's single-string pattern (URL or local path or preset name in one value), the download uses urllib directly like memryx, and _find_model_json now raises on an ambiguous multi-model directory instead of returning whichever sorts first. plugin: AxeleraDetector exposes shutdown() (the async contract hook base.py calls) instead of close(); __del__ guards a partially initialised instance. * axelera: download URL models through the atomic ModelDownloader * axelera: bring the detector unit tests in tree * init-devices: create DEVICE_ALIASES before the ACL-mode exits An alias is not an ACL grant: users running with FRIGATE_RUN_AS_ROOT or FRIGATE_DEVICE_ACLS=false still need the colon-form node the runtime enumerates, so create the aliases right after the euid check. Document DEVICE_ALIASES next to DEVICE_ACL_PATHS and note it cannot work under docker's user: mode (the container cannot write to /dev). * detectors: cover the Axelera Metis probe in test_detector_hardware * Update docs/docs/configuration/non_root.md Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * axelera: address the 2026-10-12 review round - hash directory models deterministically in compute_model_hash instead of raising IsADirectoryError at startup - keep canonical model labels addressable after user renames in the labelmap lookup (two classes can share one renamed name) - key the URL model cache by source and archive content, extract replaced archives into fresh directories, prune superseded variants conservatively - keep publishing the run duty cycle when the hardware poll has no entry (duty-only npu_usages entry instead of a hidden detector) - document the user: mode device reach instead of host-only alias creation * axelera: prune only generated cache entries A fresh download matched user-provided layouts (the docs-recommended <name>/ directory, <name>.zip archives) and look-alike model names (yolox.zip vs yolox-s-*) by prefix. Pruning is now gated on the exact generated identity pattern <name>-<source>-<32 hex digits>, so downloads never touch user-provided directories, other models, or other sources. * axelera: narrow the model path design to memryx-style zips - path is always a .zip of the compiled output (local or http(s) URL), extracted fresh on every start under a lock, like the memryx custom-model flow - _decode returns the raw class index and Frigate's labelmap names it; _build_label_lookup and _read_model_labels are gone, and the YOLOX objectness check keys off model_type - scheme-less URL support and the quantized/manifest.json fallback are dropped - width/height must equal the compiled input size; init raises otherwise instead of letterboxing - compute_model_hash is back to the unchanged file-only hashing; the .extracted marker, source/content cache-name hashes and _prune_model_cache are removed * Update frigate/test/test_axelera_detector.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * axelera: drop the run duty cycle, match the hailo temperature flow - no other accelerator reports NPU usage and the published value was time blocked in run(), not device utilization from the vendor API; removing it leaves the runner selection as the only core change - the board temperature moves to a get_hardware_temperatures branch like hailo, so it renders on the detector card; _poll_axelera, its POLLERS entry and the _scan_detectors line are gone - axelera_runtime2 is not installed: axelera.runtime imports it only inside a try for its separate new-runtime API, and the low-level API the plugin uses (Context, load_model, device_connect, load_model_instance) lives in axelera.runtime.objects * axelera: follow-ups from the 2026-10-13 review round - the offline-setup table no longer lists the axelera_runtime2 wheels, which are not installed - a failed board temperature read starts a 60s cooldown so an unresponsive axcmd does not delay every stats update * axelera: drop the model-hash test, fix the model.json error messages * axelera: drop DEVICE_ALIASES, document the CDI device spec * axelera: use ln -sf in the CDI hook example --------- Co-authored-by: Patryk Watkowski <patrykorwat@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>	2026-10-20 09:53:28 -05:00
Blake Blackshear	9b02a077e9	Merge remote-tracking branch 'origin/master' into dev	2026-10-02 06:39:23 -05:00
Mitchell CurrieandGitHub	61e50a366f	Detail XDNA2 community detector (#24480) ... * Update hardware.md Fix stray qualification * docs: add XDNA2 detector configuration * docs: add XDNA2 ZMQ model config	2026-09-28 22:49:37 -06:00
3 people	af0ba19196	Feat/deepx npu detector (#24336) ... * feat(deepx): add DEEPX NPU detector and runtime integration. * feat(deepx): enforce model_format requirement when ppu is enabled and add integrity checks for driver installation * Update frigate/detectors/plugins/deepx.py Public method lacks docstring Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Refactor DEEPX detector tests, support SSD and DAMO-YOLO * feat(deepx): add anchor-free output decoding and corresponding tests * Add tests and updates for DEEPX detector and refactor DEEPX accelerator code structure. * fix: enhance model type validation and update documentation for DEEPX detector * fix: add support for customizable score and NMS thresholds * refactor: infer YOLO layout from the model, drop per-detector options and the dxrtd placeholder * fix: keep only the anchor-free PPU verdict, re-read anchor-based each frame * Update latency data for DEEPX NPU * Expanding PPU support for DEEPX and set yolo-generic as default. * enhance scale count resolution logic * Extend PPU layout handling and YOLOX support to DEEPX detector * fix: assume the largest PPU anchor table when the .dxnn has no layout * Improve PPU decoding and introduce strides handling * Improve PPU scope and fix box format mismatch * Fix unnamed node issue that breaks traversal * fix: update object detection model type description to remove outdated architecture --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>	2026-09-21 07:50:44 -05:00
Nicolas MowenandGitHub	7821ecbb43	Migrate Hailo detector key and support hailo device (#24327) ... * Migrate Hailo detector key and support hailo device * Fix missing check	2026-09-14 08:23:36 -06:00
Josh HawkinsandGitHub	9cba1c2963	remove deepstack detector and all references to it (#24259) ... the 0.18 release notes indicated this was being removed in 0.19	2026-09-12 16:20:50 -05:00
Nicolas Mowen	27a40a507b	Implement UI for managing multiple models (#24023) ... * Implement hardware detection and UI management * Cleanup Frigate+ detection * Don't count model as changed * Fixes for audio map error * Add descriptions * Enforce that all model must exist * Fix hardware picking * Docs fixes * WebUI cleanup * Cleanup handling of scenes * UI refinement * Cleanup recommended UI * test fixews	2026-09-12 07:30:04 -06:00
Nicolas Mowen	8fe35ace3b	Refactor detector and model management (#23995) ... * Refactor detector and model management * Fix model resolution field	2026-09-12 07:30:04 -06:00
3 people	b4d5035b79	Docs: fix Synaptics default model path and warn about v4l2m2m kernel Oops on GT-BE19000AI (#24008) ... * Docs: fix Synaptics default model path in object detector docs The model is installed at /synaptics/mobilenet.synap by docker/synaptics/Dockerfile, matching the config examples in the same section. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Docs: warn about kernel Oops with v4l2m2m hwaccel on ASUS GT-BE19000AI Enabling the recommended h264_v4l2m2m hwaccel args on the GT-BE19000AI AI board (SL1680, firmware kernel 5.15.140) triggers a LIST_POISON dereference Oops in the vendor vpu driver during decoder teardown, requiring a reboot. Observed and captured on real hardware. Also fixes a Synaptics typo. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Docs: drop GT-BE19000AI hwaccel warning per review Remove the device-specific v4l2m2m kernel Oops warning as requested by maintainer review; upstream/vendor gotchas are not documented here. The Synaptics typo fix and model path correction remain. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>	2026-09-02 10:39:30 -05:00
Josh HawkinsandGitHub	4f2a297745	remove all references to degirum in frigate (#23882) ... the company ceased operations on 1 Aug 2026	2026-08-01 08:00:36 -06:00
Josh HawkinsandGitHub	e6cac50250	Miscellaneous fixes (#23651)	2026-07-08 08:27:38 -05:00
Josh HawkinsandGitHub	c99d6b0dcf	Miscellaneous fixes (#23648) ... * sort preview cameras in history by ui order * sort cameras by UI order in various components for consistent display * add no recordings faq * fix link * recording cache faq * add link * improve anchor naming in object detector docs rather than #configuration-1, #configuration-2, etc * use yaml instead of json for object detector docs * fix anchor	2026-07-07 10:56:43 -06:00