docker/rocm/Dockerfile

@@ -13,7 +13,7 @@ ARG ROCM
 
 RUN apt update -qq && \
     apt install -y wget gpg && \
-    wget -O rocm.deb https://repo.radeon.com/amdgpu-install/7.2.3/ubuntu/jammy/amdgpu-install_7.2.3.70203-1_all.deb && \
+    wget -O rocm.deb https://repo.radeon.com/amdgpu-install/7.2/ubuntu/jammy/amdgpu-install_7.2.70200-1_all.deb && \
     apt install -y ./rocm.deb && \
     apt update && \
     apt install -qq -y rocm
@@ -78,10 +78,6 @@ ENV MIGRAPHX_DISABLE_MIOPEN_FUSION=1
 ENV MIGRAPHX_DISABLE_SCHEDULE_PASS=1
 ENV MIGRAPHX_DISABLE_REDUCE_FUSION=1
 ENV MIGRAPHX_ENABLE_HIPRTC_WORKAROUNDS=1
-ENV MIOPEN_CUSTOM_CACHE_DIR=/config/model_cache/migraphx
-ENV MIOPEN_USER_DB_PATH=/config/model_cache/migraphx
-ENV AMD_COMGR_CACHE=1
-ENV AMD_COMGR_CACHE_DIR=/config/model_cache/migraphx
 
 COPY --from=rocm-dist / /
 

docker/rocm/requirements-wheels-rocm.txt

@@ -1 +1 @@
-onnxruntime-migraphx @ https://github.com/NickM-27/frigate-onnxruntime-rocm/releases/download/v7.2.3-1/onnxruntime_migraphx-1.24.4-cp311-cp311-linux_x86_64.whl
+onnxruntime-migraphx @ https://github.com/NickM-27/frigate-onnxruntime-rocm/releases/download/v7.2.0/onnxruntime_migraphx-1.23.1-cp311-cp311-linux_x86_64.whl

docker/rocm/rocm.hcl

@@ -1,5 +1,5 @@
 variable "ROCM" {
-  default = "7.2.3"
+  default = "7.2.0"
 }
 variable "HSA_OVERRIDE_GFX_VERSION" {
   default = ""

docs/docs/configuration/object_detectors.md

@@ -1022,12 +1022,12 @@ detectors:
 
 ### ONNX Supported Models
 
-| Model                                | Nvidia GPU | AMD GPU | Notes                                               |
+| Model                         | Nvidia GPU | AMD GPU | Notes                                               |
-| ------------------------------------ | ---------- | ------- | --------------------------------------------------- |
+| ----------------------------- | ---------- | ------- | --------------------------------------------------- |
-| [YOLOv9](#yolo-v3-v4-v7-v9-2)        | ✅         | ✅      | Supports CUDA Graphs for optimal Nvidia performance |
+| [YOLOv9](#yolo-v3-v4-v7-v9-2) | ✅         | ✅      | Supports CUDA Graphs for optimal Nvidia performance |
-| [RF-DETR](#rf-detr)                  | ✅         | ⚠️      | Supports CUDA Graphs for optimal Nvidia performance |
+| [RF-DETR](#rf-detr)           | ✅         | ❌      | Supports CUDA Graphs for optimal Nvidia performance |
-| [YOLO-NAS](#yolo-nas-1)              | ⚠️         | ⚠️      | Not supported by CUDA Graphs                        |
+| [YOLO-NAS](#yolo-nas-1)       | ⚠️         | ⚠️      | Not supported by CUDA Graphs                        |
-| [YOLOX](#yolox-1)                    | ✅         | ✅      | Supports CUDA Graphs for optimal Nvidia performance |
+| [YOLOX](#yolox-1)             | ✅         | ✅      | Supports CUDA Graphs for optimal Nvidia performance |
 | [D-FINE / DEIMv2](#d-fine--deimv2-1) | ⚠️         | ❌      | Not supported by CUDA Graphs                        |
 
 There is no default model provided, the following formats are supported:

docs/docs/frigate/hardware.md

@@ -223,11 +223,10 @@ Apple Silicon can not run within a container, so a ZMQ proxy is utilized to comm
 
 With the [ROCm](../configuration/object_detectors.md#amdrocm-gpu-detector) detector Frigate can take advantage of many discrete AMD GPUs.
 
-| Name           | YOLOv9 Inference Time       | YOLO-NAS Inference Time   | RF-DETR Inference Time |
+| Name      | YOLOv9 Inference Time       | YOLO-NAS Inference Time   |
-| -------------- | --------------------------- | ------------------------- | ---------------------- |
+| --------- | --------------------------- | ------------------------- |
-| AMD 780M       | t-320: ~ 14 ms s-320: 20 ms | 320: ~ 25 ms 640: ~ 50 ms |                        |
+| AMD 780M  | t-320: ~ 14 ms s-320: 20 ms | 320: ~ 25 ms 640: ~ 50 ms |
-| AMD 8700G      |                             | 320: ~ 20 ms 640: ~ 40 ms |                        |
+| AMD 8700G |                             | 320: ~ 20 ms 640: ~ 40 ms |
-| AMD 9060XT 16G | t-320: ~ 4 ms  s-320: 5 ms  | 320: ~ 6 ms               | Nano-320: ~ 90 ms      |
 
 ## Community Supported Detectors
 

frigate/data_processing/real_time/face.py

@@ -229,10 +229,9 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
                 logger.debug(f"No person box available for {id}")
                 return
 
-            # YuNet (cv2.FaceDetectorYN) is trained on BGR
+            rgb = cv2.cvtColor(frame, cv2.COLOR_YUV2RGB_I420)
-            bgr = cv2.cvtColor(frame, cv2.COLOR_YUV2BGR_I420)
             left, top, right, bottom = person_box
-            person = bgr[top:bottom, left:right]
+            person = rgb[top:bottom, left:right]
             face_box = self.__detect_face(person, self.face_config.detection_threshold)
 
             if not face_box:
@@ -251,6 +250,11 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
                 )
                 return
 
+            try:
+                face_frame = cv2.cvtColor(face_frame, cv2.COLOR_RGB2BGR)
+            except Exception as e:
+                logger.debug(f"Failed to convert face frame color for {id}: {e}")
+                return
         else:
             # don't run for object without attributes
             if not obj_data.get("current_attributes"):

frigate/detectors/detection_runners.py

@@ -132,6 +132,7 @@ class ONNXModelRunner(BaseModelRunner):
         return model_type in [
             EnrichmentModelTypeEnum.paddleocr.value,
             EnrichmentModelTypeEnum.jina_v2.value,
+            EnrichmentModelTypeEnum.arcface.value,
             ModelTypeEnum.rfdetr.value,
             ModelTypeEnum.dfine.value,
         ]