Object Detection YOLOv5 3.1 won't start
-
Hello, I am trying to run Blue Iris with CP AI Object detection on Windows Server 2022 Datacenter. I am using a Quadro 4000. I have Cuda 10.1 installed and CUDNN files copied into the folders. YOLO5 6.2 installed and is running fine though. I'm only trying to run YOLO5 because I'm reading that it's the only one that works for CUDA 10.1, and that CUDA 10.1 is the only CUDA that works for a Quadro 4000? I'm really not sure about any of this as I'm new to it all. What should I be using, what am I doing wrong? Here's some log info:
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.20348)
CPUs: Intel(R) Xeon(R) CPU E5-2609 0 @ 2.40GHz (Intel)
2 CPUs x 4 cores. 4 logical processors (x64)
GPU (Primary): (NVIDIA), CUDA: 10.1.105 (up to: ), Compute: , cuDNN: 8.5
System RAM: 64 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.20
.NET SDK: 7.0.410
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA Quadro 4000:
Driver Version 21.21.13.7783
Video Processor Quadro 4000
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = CPAI_PORT = 32168-----------------------------------------------------------
12:22:48:Started Object Detection (YOLOv5 3.1) module
12:22:50:detect_adapter.py: Traceback (most recent call last):
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\detect_adapter.py", line 19, in
12:22:50:detect_adapter.py: from process import YOLODetector, init_detect
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\process.py", line 14, in
12:22:50:detect_adapter.py: from models.experimental import attempt_load
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\experimental.py", line 6, in
12:22:50:detect_adapter.py: from models.common import Conv, DWConv
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\common.py", line 6, in
12:22:50:detect_adapter.py: from utils.general import non_max_suppression
12:22:50:detect_adapter.py: File "C:\P -
Hello, I am trying to run Blue Iris with CP AI Object detection on Windows Server 2022 Datacenter. I am using a Quadro 4000. I have Cuda 10.1 installed and CUDNN files copied into the folders. YOLO5 6.2 installed and is running fine though. I'm only trying to run YOLO5 because I'm reading that it's the only one that works for CUDA 10.1, and that CUDA 10.1 is the only CUDA that works for a Quadro 4000? I'm really not sure about any of this as I'm new to it all. What should I be using, what am I doing wrong? Here's some log info:
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.20348)
CPUs: Intel(R) Xeon(R) CPU E5-2609 0 @ 2.40GHz (Intel)
2 CPUs x 4 cores. 4 logical processors (x64)
GPU (Primary): (NVIDIA), CUDA: 10.1.105 (up to: ), Compute: , cuDNN: 8.5
System RAM: 64 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.20
.NET SDK: 7.0.410
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA Quadro 4000:
Driver Version 21.21.13.7783
Video Processor Quadro 4000
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = CPAI_PORT = 32168-----------------------------------------------------------
12:22:48:Started Object Detection (YOLOv5 3.1) module
12:22:50:detect_adapter.py: Traceback (most recent call last):
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\detect_adapter.py", line 19, in
12:22:50:detect_adapter.py: from process import YOLODetector, init_detect
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\process.py", line 14, in
12:22:50:detect_adapter.py: from models.experimental import attempt_load
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\experimental.py", line 6, in
12:22:50:detect_adapter.py: from models.common import Conv, DWConv
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\common.py", line 6, in
12:22:50:detect_adapter.py: from utils.general import non_max_suppression
12:22:50:detect_adapter.py: File "C:\P -
Hello, I am trying to run Blue Iris with CP AI Object detection on Windows Server 2022 Datacenter. I am using a Quadro 4000. I have Cuda 10.1 installed and CUDNN files copied into the folders. YOLO5 6.2 installed and is running fine though. I'm only trying to run YOLO5 because I'm reading that it's the only one that works for CUDA 10.1, and that CUDA 10.1 is the only CUDA that works for a Quadro 4000? I'm really not sure about any of this as I'm new to it all. What should I be using, what am I doing wrong? Here's some log info:
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.20348)
CPUs: Intel(R) Xeon(R) CPU E5-2609 0 @ 2.40GHz (Intel)
2 CPUs x 4 cores. 4 logical processors (x64)
GPU (Primary): (NVIDIA), CUDA: 10.1.105 (up to: ), Compute: , cuDNN: 8.5
System RAM: 64 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.20
.NET SDK: 7.0.410
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA Quadro 4000:
Driver Version 21.21.13.7783
Video Processor Quadro 4000
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = CPAI_PORT = 32168-----------------------------------------------------------
12:22:48:Started Object Detection (YOLOv5 3.1) module
12:22:50:detect_adapter.py: Traceback (most recent call last):
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\detect_adapter.py", line 19, in
12:22:50:detect_adapter.py: from process import YOLODetector, init_detect
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\process.py", line 14, in
12:22:50:detect_adapter.py: from models.experimental import attempt_load
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\experimental.py", line 6, in
12:22:50:detect_adapter.py: from models.common import Conv, DWConv
12:22:50:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\common.py", line 6, in
12:22:50:detect_adapter.py: from utils.general import non_max_suppression
12:22:50:detect_adapter.py: File "C:\PThanks very much for your report. I don't think I've seen someone test with a Quadro 4000 before. Please try disabling half-precision, see if that helps.
Thanks, Sean Ewington CodeProject