# How to Use Furiosa SDK from Start to Finish 예제 관련 오류 **URL:** \ **Category:** 일반\ **Created:** [October 5, 2023, 3:26am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91 "2023-10-05T03:26:38Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![321mkdpewr](https://avatars.discourse-cdn.com/v4/letter/3/58956e/32.png) [@321mkdpewr](https://forums.furiosa.ai/u/321mkdpewr)\ **Post date:** [October 5, 2023, 3:26am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91/1 "2023-10-05T03:26:38Z")
> 위 링크의 예제를 실행하던 중 ![스크린샷, 2023-10-05 12-17-20](https://canada1.discourse-cdn.com/flex031/uploads/furiosa_ai/original/1X/0c07c10ff52711e4c73fced0e52b2ecae6697aab.png) 위 영역에서 입출력 에러가 발생합니다. 에러내용은 아래와 같습니다. uNpuDrv (E) [npu\_pdma\_to\_device\_sync:370] ioctl(PDMA\_TO\_DEVICE) failed[57224.196073668] uNpuDrv (E) [\_\_submit\_bio:620] write failed, Input/output error uNpuDrv (E) [npu\_pdma\_from\_device\_sync:388] ioctl(PDMA\_FROM\_DEVICE) failed[57274.424496334] uNpuDrv (E) [dma\_from\_device\_sync:690] read failed, Input/output error ![스크린샷, 2023-10-05 12-17-47](https://canada1.discourse-cdn.com/flex031/uploads/furiosa_ai/original/1X/6d107f25c158bbbfe29867709c41811637bd6af0.png) 그리고 예제 실행 결과 첫번째 실행에서 예제와 달리 지연이 12ms가 아닌 133ms로 차이가 납니다. 두번째 실행에서 정확도가 조금 떨어지고 지연이 1ms 증가합니다. 환경셋팅 ![스크린샷, 2023-10-05 12-26-02](https://canada1.discourse-cdn.com/flex031/uploads/furiosa_ai/original/1X/ed0bb5b1f77f979b4667d49f5b0bb6735f03fd97.png) 혹시 제가 뭔가를 빠트린 걸까요? 예제를 다시 확인하고 두번째로 실행해도 같은 오류와 긴 지연시간이 발생합니다. ---
**Author:** ![dreameye98](https://yyz1.discourse-cdn.com/flex031/user_avatar/forums.furiosa.ai/dreameye98/32/8_2.png) [@dreameye98](https://forums.furiosa.ai/u/dreameye98)\ **Post date:** [October 5, 2023, 4:38am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91/2 "2023-10-05T04:38:18Z")
안녕하세요 FuriosaAI 정영범입니다. 카카오 클라우드에서 사용하시는 것으로 보이는데 맞을까요? 소속 회사를 알려주시면 카카오에 문의해서 해당 pod을 살펴보겠습니다. Pod을 다시 생성해야 할 수도 있으니 중요한 파일이 있다면 백업을 부탁 드립니다. ---
**Author:** ![321mkdpewr](https://avatars.discourse-cdn.com/v4/letter/3/58956e/32.png) [@321mkdpewr](https://forums.furiosa.ai/u/321mkdpewr)\ **Post date:** [October 5, 2023, 4:50am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91/3 "2023-10-05T04:50:05Z")
카카오 클라우드에서 사용하는 것이 아닙니다. 개인용 우분투 20.04에서 설치해서 진행중입니다. 실리콘아츠입니다. ---
**Author:** ![dreameye98](https://yyz1.discourse-cdn.com/flex031/user_avatar/forums.furiosa.ai/dreameye98/32/8_2.png) [@dreameye98](https://forums.furiosa.ai/u/dreameye98)\ **Post date:** [October 5, 2023, 4:57am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91/4 "2023-10-05T04:57:48Z")
답변 감사합니다. 정확한 원인 파악을 위해 아래와 같이 실행을 해주시겠어요? `git clone https://github.com/furiosa-ai/furiosa-sdk` `cd ./furiosa-sdk/examples/inferences` `./image_classify.py ../assets/images/car.jpg` ---
**Author:** ![321mkdpewr](https://avatars.discourse-cdn.com/v4/letter/3/58956e/32.png) [@321mkdpewr](https://forums.furiosa.ai/u/321mkdpewr)\ **Post date:** [October 5, 2023, 6:40am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91/5 "2023-10-05T06:40:53Z")
![스크린샷, 2023-10-05 16-42-25](https://canada1.discourse-cdn.com/flex031/uploads/furiosa_ai/original/1X/fe6b20f5f65237743b95fdc46f9f8e8a2a258180.png) 위는 셋팅 환경입니다. gpu는 없고 2200g cpu에 그래픽카드가 내장되어 있는 걸로 알고 있습니다. (furiosa) nobleteam@nobleteam-desktop:~/furiosa-sdk/examples/inferences$ ./image\_classify.py …/assets/images/car.jpg libfuriosa\_hal.so — v0.11.0, built @ 43c901f Loading and compiling the model /home/nobleteam/furiosa-sdk/examples/inferences/…/assets/quantized\_models/imagenet\_224x224\_mobilenet\_v1\_uint8\_quantization-aware-trained\_dm\_1.0\_without\_softmax.tflite 2023-10-05T06:37:20.503516Z INFO furiosa\_rt\_core::driver::event\_driven::coord: FuriosaRT (v0.10.1, rev: e710d5f8c, built at: 2023-09-22T00:49:24Z) bootstrapping … 2023-10-05T06:37:20.508989Z INFO furiosa\_rt\_core::driver::event\_driven::coord: Found furiosa-compiler (v0.10.0, rev: f8f05c8, built at: 2023-08-08T11:58:09Z) 2023-10-05T06:37:20.509012Z INFO furiosa\_rt\_core::driver::event\_driven::coord: Found libhal (type: warboy, v0.11.0, rev: 43c901f built at: 2023-08-08T12:07:35Z) 2023-10-05T06:37:20.509020Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Runtime-0] detected 1 NPU device(s): 2023-10-05T06:37:20.514607Z INFO furiosa\_rt\_core::driver::event\_driven::coord: - [0] npu:0:0-1 (warboy-b0-2pe, 128dpes, firmware: 1.7.2, e1c4288) 2023-10-05T06:37:20.515227Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Runtime-0] started 2023-10-05T06:37:20.520972Z INFO furiosa::runtime: Saving the compilation log into /home/nobleteam/.local/state/furiosa/logs/compiler-20231005153720-d1apag.log 2023-10-05T06:37:20.527292Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Runtime-0] created Sess-148e3f60 using npu:0:0-1 2023-10-05T06:37:20.535108Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Sess-148e3f60] compiling the model (target: warboy-b0-2pe, 128dpes, file: imagenet\_224x224\_mobilenet\_v1\_uint8\_quantization-aware-trained\_dm\_1.0\_without\_softmax.tflite, size: 4.1 MiB) [1/6] 🔍 Compiling from tflite to dfg Done in 0.13302933s [2/6] 🔍 Compiling from dfg to ldfg ▪▪▪▪▪ [1/3] Splitting graph(LAS)…Done in 45.51663s ▪▪▪▪▪ [2/3] Lowering graph(LAS)…Done in 19.62021s ▪▪▪▪▪ [3/3] Optimizing graph…Done in 1.7741942s Done in 67.16383s [3/6] 🔍 Compiling from ldfg to cdfg Done in 0.001475751s [4/6] 🔍 Compiling from cdfg to gir Done in 0.012820173s [5/6] 🔍 Compiling from gir to lir Done in 0.004127534s [6/6] 🔍 Compiling from lir to enf Done in 0.0331447s ✨ Finished in 67.34916s 2023-10-05T06:38:28.333163Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Sess-148e3f60] the model compile is successful (took 67 secs) 2023-10-05T06:38:28.417020Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Runtime-0] created 1 NPU threads on npu:0:0-1 (DRAM: 228.0 kiB/16.0 GiB, SRAM: 5.7 MiB/128.0 MiB) Model has been compiled successfully Model input and output: ./image\_classify.py:32: FutureWarning: `Session.print_summary` is deprecated, use `Session.model.print_summary` instead. print(sess.print\_summary()) Inputs: {0: TensorDesc(name=“input”, shape=(1, 224, 224, 3), dtype=UINT8, format=NHWC, size=150528, len=150528)} Outputs: {0: TensorDesc(name=“MobilenetV1/Logits/Conv2d\_1c\_1x1/BiasAdd”, shape=(1, 1, 1, 1001), dtype=UINT8, format=NHWC, size=1001, len=1001)} None ./image\_classify.py:34: FutureWarning: `Session.input` is deprecated, use `Session.model.input` instead. \_, height, width, channel = sess.input(0).shape Prediction elapsed 0.01 secs [Top 5 scores:] sports car: 155 pickup: 152 car wheel: 148 convertible: 148 racer: 143 2023-10-05T06:38:28.461348Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Sess-148e3f60] terminated 2023-10-05T06:38:28.465750Z INFO furiosa\_rt\_core::npu::raw: NPU (npu:0:0-1) has been closed 2023-10-05T06:38:28.468136Z INFO furiosa\_rt\_core::driver::event\_driven::coord: [Runtime-0] stopped ---
**Author:** ![dreameye98](https://yyz1.discourse-cdn.com/flex031/user_avatar/forums.furiosa.ai/dreameye98/32/8_2.png) [@dreameye98](https://forums.furiosa.ai/u/dreameye98)\ **Post date:** [October 5, 2023, 8:03am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91/6 "2023-10-05T08:03:14Z")
로그를 보면 잘 동작하는 것으로 보입니다. 재부팅하시고 첫 예제를 다시 실행해보시겠어요? ---
**Author:** ![321mkdpewr](https://avatars.discourse-cdn.com/v4/letter/3/58956e/32.png) [@321mkdpewr](https://forums.furiosa.ai/u/321mkdpewr)\ **Post date:** [October 5, 2023, 8:09am UTC](https://forums.furiosa.ai/t/how-to-use-furiosa-sdk-from-start-to-finish/91/7 "2023-10-05T08:09:40Z")
아… 재부팅 생각을 못했네요 재부팅하고 다시 시도해보겠습니다. 감사합니다.