• [问题求助] 机械臂夹爪 抓不住方块
    请问 夹爪参数在哪里改 是garbage_grap文件吗?修改了self.grap_joint之后,爪子抓取力度并没有发生变化。
  • [问题求助] 模型推理
    原始模型的输入是三个维度我转换为om的维度是(1,640,640,3)四个维度,现在推理失败,原因是形状问题我看了下atc工具必须是nchw或者nhwc这样子的,三个维度的话转换不了吧,想看下各位大佬有什么解决办法没有
  • [AI类] om模型转换——mobilesam模型onnx转换(精度问题)
    将mobilesam的onnx模型转换为om模型,以下是我的转换命令和报错信息。请问该如何处理呢?
  • [问题求助] AMCT安装问题
    安装好AMCT后,import amct_onnx as amct出现以下错误:The given version [9] is not supported, only version 1 to 8 is supported in this build. Segmentation fault (core dumped) 
  • [其他] 【atc模型转换报错】onnx->om模型转换 一直报E40001 python动态库非法
    模型转换从onnx到om 使用atc转换。 python版本3.10.  cann 版本为8.0。芯片 ascend310p duo报如下错误。当前根据如下文档转换的,先把stable diffusion模型转到onnx, 然后onnx转到om模型。https://gitee.com/ascend/ModelZoo-PyTorch/blob/master/ACL_PyTorch/built-in/foundation_models/stable_diffusion/README.md安装路径
  • [问题求助] atlas-util库编译遇到问题
    功能模块】参照博客步骤:https://gitee.com/ascend/samples/blob/master/cplusplus/environment/atlasutil_install/README_200DK_CN.md【操作步骤&问题现象】1、已设置对应的环境变量:export DDK_PATH=/home/HwHiAiUser/Ascend/ascend-toolkit/latest/arm64-linux 2、make报错【截图信息】echo - do [do_pre_build] - do [do_pre_build] mkdir -p ./out/arm/obj echo [CC] out/arm/obj/src/camera.o [CC] out/arm/obj/src/camera.o mkdir -p out/arm/obj/src/ aarch64-linux-gnu-g++ -I./include -I/home/HwHiAiUser/Ascend/driver/ -I/home/HwHiAiUser/ascend_ddk/arm/include/ -I/home/HwHiAiUser/ascend_ddk/arm/include/ascenddk/ -I/home/HwHiAiUser/ascend_ddk/arm/include/ascenddk/presenter/agent/ -I/home/HwHiAiUser/Ascend/ascend-toolkit/latest/acllib/include/ -I/home/HwHiAiUser/Ascend/ascend-toolkit/latest/atc/include/protobuf -DENABLE_DVPP_INTERFACE -std=c++11 -fPIC -Wall -O2 -DENABLE_BOARD_CAMARE -I./include -I/home/HwHiAiUser/Ascend/driver/ -I/home/HwHiAiUser/ascend_ddk/arm/include/ -I/home/HwHiAiUser/ascend_ddk/arm/include/ascenddk/ -I/home/HwHiAiUser/ascend_ddk/arm/include/ascenddk/presenter/agent/ -I/home/HwHiAiUser/Ascend/ascend-toolkit/latest/acllib/include/ -I/home/HwHiAiUser/Ascend/ascend-toolkit/latest/atc/include/protobuf -c -fstack-protector-all src/camera.cpp -o out/arm/obj/src/camera.o Assembler messages: Fatal error: can't create out/arm/obj/src/camera.o: Permission denied Makefile:96: recipe for target 'out/arm/obj/src/camera.o' failed make: *** [out/arm/obj/src/camera.o] Error 1 
  • [问题求助] 昇腾A800 900 A2 服务器安装MegaRAID 9569 8i卡后 带宽降速
    昇腾A800 900 A2 服务器安装MegaRAID 9569 8i卡后 带宽降速 带宽规格x8 ,当前规格x4os版本 openeuler22.03
  • [其他] 生成的AscendP3的OM模型可用,而生成的AscendB4的OM模型不可用
    我是用ATC生成AscendP3的模型可用,命令如下:atc --framework=5 --model=./fairmot.onnx --input_format=NCHW --input_shape="actual_input_1:1,3,2048,512" --output=./fairmot_bs1 --log=error --soc_version=Ascend310P3在300I上正确推理,同样的模型,用:atc --framework=5 --model=./fairmot.onnx --input_format=NCHW --input_shape="actual_input_1:1,3,2048,512" --output=./fairmot_bs1_B4 --log=error --soc_version=Ascend310B4生成ascend310B4在200 DK上报错,报错内容如下:(FairMot) HwHiAiUser@davinci-mini:~/altas/project/FairMOT/test$ python3 -m ais_bench --model fairmot_bs1_B4.om --input ./pre_dataset/ --output ./out --output_dirname result --outfmt BIN[INFO] acl init success[INFO] open device 0 successE19999: Inner Error!Get stub function failed, name=1351718655777264385_trans_Cast_0.[FUNC:GetFunctionByName][FILE:logger.cc][LINE:91]rtGetFunctionByName execute failed, reason=[kernel lookup error][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50]E19999 Call rtGetFunctionByName failed op:trans_Cast_0(Cast), bin_file_key:1351718655777264385_trans_Cast_0, ret:0x7BC93[FUNC:InitTVMTask][FILE:kernel_task_info.cc][LINE:1167]TraceBack (most recent call last):Task index:1 init failed, ret:507027.[FUNC:InitTaskInfo][FILE:davinci_model.cc][LINE:3818][Model][FromData]load model from data failed, ge result[507027][FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161][ERROR] load model from file failed, model file is fairmot_bs1_B4.om[WARN] Check failed:processModel->LoadModelFromFile(modelPath), ret:1[WARN] no model had been loaded, unload failedTraceback (most recent call last):File "/home/HwHiAiUser/.conda/envs/FairMot/lib/python3.7/runpy.py", line 193, in _run_module_as_main"__main__", mod_spec)File "/home/HwHiAiUser/.conda/envs/FairMot/lib/python3.7/runpy.py", line 85, in _run_codeexec(code, run_globals)File "/home/HwHiAiUser/.conda/envs/FairMot/lib/python3.7/site-packages/ais_bench/__main__.py", line 18, inexec(open(os.path.join(cur_path, "infer/__main__.py")).read())File "", line 280, inFile "/home/HwHiAiUser/.conda/envs/FairMot/lib/python3.7/site-packages/ais_bench/infer/infer_process.py", line 752, in infer_processmain(args)File "/home/HwHiAiUser/.conda/envs/FairMot/lib/python3.7/site-packages/ais_bench/infer/infer_process.py", line 428, in mainsession = init_inference_session(args, tmp_acl_json_path if tmp_acl_json_path is not None else acl_json_path)File "/home/HwHiAiUser/.conda/envs/FairMot/lib/python3.7/site-packages/ais_bench/infer/infer_process.py", line 115, in init_inference_sessionsession = InferSession(args.device, args.model, acl_json_path, args.debug, args.loop)File "/home/HwHiAiUser/.conda/envs/FairMot/lib/python3.7/site-packages/ais_bench/infer/interface.py", line 94, in __init__self.session = aclruntime.InferenceSession(self.model_path, self.device_id, self.options)RuntimeError: [1][ACL: invalid parameter][INFO] end to reset device 0[INFO] end to finalize acl文件信息如下:(FairMot) HwHiAiUser@davinci-mini:~/altas/project/FairMOT/test$ ls -ltotal 123140-r--r--r-- 1 HwHiAiUser HwHiAiUser 41906916 Mar 1 20:33 fairmot_bs1.om-r--r--r-- 1 HwHiAiUser HwHiAiUser 42070773 Mar 1 20:33 fairmot_bs1_B1.om-r--r--r-- 1 HwHiAiUser HwHiAiUser 42071677 Mar 2 21:58 fairmot_bs1_B4.om-rw-rw-r-- 1 HwHiAiUser HwHiAiUser 5412 Mar 1 20:31 fairmot_postprocess.pydrwx------ 2 HwHiAiUser HwHiAiUser 4096 Mar 3 21:49 outdr-xr-xr-x 2 HwHiAiUser HwHiAiUser 4096 Mar 1 20:31 pre_dataset-rw-rw-r-- 1 HwHiAiUser HwHiAiUser 8970 Mar 1 20:31 test.py系统报507027错误,可能是什么原因?模型太大?
  • [问题求助] mdc610
    请问mdc610上能否支持是用AscendCL 做AI模型的推理,求解答。
  • [问题求助] acl init failed, errorCode = 100039
    在atlas 300I的硬件中执行了两个自己的项目。其中第一个项目初始执行时报错acl init failed, errorCode = 100039,通过source ~/.bashrc命令解决了。但是第二个项目仍报错acl init failed, errorCode = 100039,并且无法解决,请问是什么问题?npu-smi info是可以被正确执行的。
  • [问题求助] Fairmot推理报错
    我使用https://gitee.com/ascend/ModelZoo-PyTorch/tree/master/ACL_PyTorch/contrib/cv/detection/FairMOT时,严格按照readme文件操作,前面全部成功,最后运行:python3 fairmot_postprocess.py --data_dir=./dataset  --input_root=/home/HwHiAiUser/test/out/result 时,报错:Fix size testing. training chunk_sizes: [6, 6] The output will be saved to  ./FairMOT/src/lib/../../exp/mot/default heads {'hm': 1, 'wh': 4, 'id': 128, 'reg': 2} 2024-02-16 16:10:09 [INFO]: start seq: MOT17-02-SDP 2024-02-16 16:10:09 [INFO]: start seq: MOT17-02-SDP Traceback (most recent call last):   File "fairmot_postprocess.py", line 153, in <module>     save_videos=False)   File "fairmot_postprocess.py", line 66, in process     nf, ta, tc = eval_seq(opt, dataloader, data_type, result_filename, seq,save_dir=output_dir, show_image=show_image, frame_rate=frame_rate)   File "fairmot_postprocess.py", line 104, in eval_seq     hm_eval = torch.from_numpy(np.fromfile(dataloader[i + 3], dtype='float32').reshape(1, 1, 152, 272)) ValueError: cannot reshape array of size 82688 into shape (1,1,152,272) 请问为什么?如何解决?我的环境,ubuntu20.04 kernel:5.4.0-26-generic  ;Ascend310P3;torch 1.5;python 3.7
  • [问题求助] atlas300P3 在容器中访问rtsp流地址报错No route to host
    [tcp @ 0xfffa98170af0] Connection attempt to 10.x.x.x port 554 failed: No route to host[tcp @ 0xfffa98170af0] Connection to tcp://10.x.x.x?timeout=5000000 failed: No route to host[ERROR]  Could not open video:rtsp://admin:@xxx@10.x.x.x:554/Streaming/Channels/101, return :-113, error info:No route to host[ERROR]  Open rtsp://admin:@xxx@10.x.x.x:554/Streaming/Channels/101 failed[ERROR]  Not support stream, type 0,  profile 0[ERROR]  Video rtsp://admin:@xxx@10.x.x.x:554/Streaming/Channels/101 type is invalid[ERROR]  Open rtsp://admin:@xxx@10.x.x.x:554/Streaming/Channels/101 failed for init ffmpeg error: 601[INFO]  Video rtsp://admin:@xxx@10.x.x.x:554/Streaming/Channels/101 decode status -1[ERROR]  Failed to open video[ERROR]  Init resource failedDAMN ! worker 1 (pid: 71959) died, killed by signal 11 :( trying respawn ...Respawned uWSGI worker 1 (new pid: 72303)
  • [技术干货] 2024年1月人工智能问题总结合集
    一月问题总结如下:【1】用华为atlas300-3010 用于训练失败cid:link_3【2】如何展示这些图片呢cid:link_4【3】云平台第一次用,求助怎么导入transformers库啊?cid:link_0【4】 atlas 200 DK 制卡完成后启动不了cid:link_1【5】请问下,新人申请预测大模型一般几天可以通过申请。cid:link_2
  • [问题求助] atlas 200 DK 制卡完成后启动不了
    一直只有最右边的3559 VEDIO 灯亮着,而且时不时闪烁
  • [AI类] atc转模型时报错提示E19024: Value
     haitu@ubuntu:~$ export ASCEND_OPP_PATH=/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp:$ASCEND_OPP_PATH haitu@ubuntu:~$ atc --model=/home/haitu/module/ResNet50/resnet50.prototxt --weight=/home/haitu/module/ResNet50/resnet50.caffemodel --framework=0 --output=/home/haitu/module/ResNet50/out/caffe_resnet50 --soc_version=Ascend310 ATC start working now, please wait for a moment. ATC run failed, Please check the detail log, Try 'atc --help' for more information E19024: Value [/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp:/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp:/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp:] for environment variable [ASCEND_OPP_PATH] is invalid when loading the tiling lib.         [GraphOpt][Init][InitOpsPath] Ascend opp path is empty.[FUNC:InitAscendOpsPath][FILE:configuration.cc][LINE:459]         [GraphOpt][Init] Failed to load ascend ops path.[FUNC:Initialize][FILE:configuration.cc][LINE:106]         [FusionMngr][Init] Failed to initialize configuration, return status is [53608456][FUNC:Initialize][FILE:fusion_manager.cc][LINE:316]         PluginManager InvokeAll failed.[FUNC:Initialize][FILE:ops_kernel_manager.cc][LINE:94]         OpsManager initialize failed.[FUNC:InnerInitialize][FILE:gelib.cc][LINE:139]         GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:93]  haitu@ubuntu:~$ vi /home/haitu/.bashrc  haitu@ubuntu:~$ source ~/.bashrc  haitu@ubuntu:~$ atc --model=/home/haitu/module/ResNet50/resnet50.prototxt --weight=/home/haitu/module/ResNet50/resnet50.caffemodel --framework=0 --output=/home/haitu/module/ResNet50/out/caffe_resnet50 --soc_version=Ascend310 ATC start working now, please wait for a moment. ATC run failed, Please check the detail log, Try 'atc --help' for more information E19024: Value [/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp:/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp:/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp::/home/haitu/Ascend/ascend-toolkit/5.13.t5.0.b050/x86_64-linux/opp] for environment variable [ASCEND_OPP_PATH] is invalid when loading the tiling lib.         [GraphOpt][Init][InitOpsPath] Ascend opp path is empty.[FUNC:InitAscendOpsPath][FILE:configuration.cc][LINE:459]         [GraphOpt][Init] Failed to load ascend ops path.[FUNC:Initialize][FILE:configuration.cc][LINE:106]         [FusionMngr][Init] Failed to initialize configuration, return status is [53608456][FUNC:Initialize][FILE:fusion_manager.cc][LINE:316]         PluginManager InvokeAll failed.[FUNC:Initialize][FILE:ops_kernel_manager.cc][LINE:94]         OpsManager initialize failed.[FUNC:InnerInitialize][FILE:gelib.cc][LINE:139]         GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:93]