问题遇到的现象和发生背景
argis pro 3.0 深度学习 影像分析-使用深度学习检测对象,使用CPU可以运行,但是使用GPU不行。
Detect Objects Using Deep Learning
Parameters
Input Raster C:\yt\gffff.tif
Output Detected Objects C:\Users\Administrator\Documents\ArcGIS\Projects\MyProject5\MyProject5.gdb\gffff_DetectObjectsUsingDeep1
Model Definition C:\yt\TEST\BuildingFootprintExtraction_China.dlpk
Arguments padding 256;batch_size 4;threshold 0.9;return_bboxes False;tile_size 1024
Non Maximum Suppression NMS
Confidence Score Field Confidence
Class Value Field Class
Max Overlap Ratio 0
Processing Mode PROCESS_AS_MOSAICKED_IMAGE
Output Classified Raster
=====================
Environments
Processor Type GPU
Messages
Start Time: 2022年11月26日 23:57:24
ERROR 999999: Something unexpected caused the tool to fail. Contact Esri Technical Support (http://esriurl.com/support) to Report a Bug, and refer to the error help for potential solutions or workarounds.
Parallel processing job timed out [Failed to generate table]
Parallel processing job timed out [Failed to generate table]
Failed to execute (DetectObjectsUsingDeepLearning).
Failed at 2022年11月26日 23:57:31 (Elapsed Time: 6.84 seconds)
用代码块功能插入代码,请勿粘贴截图
with arcpy.EnvManager(processorType="GPU"):
out_classified_raster = arcpy.ia.DetectObjectsUsingDeepLearning(r"C:\yt\gffff.tif", r"C:\Users\Administrator\Documents\ArcGIS\Projects\MyProject5\MyProject5.gdb\gffff_DetectObjectsUsingDeep1", r"C:\yt\TEST\BuildingFootprintExtraction_China.dlpk", "padding 256;batch_size 4;threshold 0.9;return_bboxes False;tile_size 1024", "NMS", "Confidence", "Class", 0, "PROCESS_AS_MOSAICKED_IMAGE"); out_classified_raster.save(None)
我的解答思路和尝试过的方法
装过cuda,cudnn,经检测环境没问题。电脑只有一个显卡,安装的最新驱动。深度学习包是官方下载的,3.0的,没有问题。环境是默认环境,使用克隆与否都是不能用GPU.
我想要达到的结果
请指教,如何能使用GPU进行深度学习?感谢您的帮助!