Default Avatar

Ethon Lin

Ethon Lin

About

Username
Ethon Lin
Joined
Visits
1,159
Last Active
Roles
Member, ModeratorsKL520, ModeratorsKL720, ModeratorsAIModel

Comments

  • 在Linux環境下，USB的存取是需要管理者權限的，但管理者權限下的環境與一般環境會有差異，也代表即便先前安裝好了python環境，若是在執行時改用sudo python 指令，則會發生找不到相關lib的python error。 為避免usb權限以及python環境安裝的問題，建議可以照下面做法來…
    in KL520_Update_FW fail Comment by Ethon Lin August 2021
  • add devices failed代表電腦與dongle連接時發生錯誤，有可能是電腦環境的問題，也可能是dongle端fw的問題，可以透過下面幾個步驟檢查 所使用的電腦為X86? X64?ARM? 所使用的OS為 Win10? ubuntu? 版本為? 是否所需要的library使否都有安裝? python是否為3.8以上版本? …
    in KL520_Update_FW fail Comment by Ethon Lin August 2021
  • 新的錯誤訊息看起來是找不到檔案dme_async_pre_post_host_yolov5.py，可以先確認/host_lib/python/examples_kl520/中是否有此檔案，此範例要使用競賽專用的專案 host_lib_competition.zip中才有
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • 如果是cam的範例正常但兩張照片的範例會出錯的話可以檢查是否有安裝 pip install image 這個library，在dme_async_pre_post_host_yolov5這個範例中會透過"image"這個lib來處理照片 https://www.kneron.com/forum/uploads/550/8PM48T9SFK6E.jpg
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • 確認了一下，有幾個環境設定可檢查一下，如下是我conda中的環境，安裝的是python 3.8.5，在同一個環境中使用指令python的確可以執行到3.8.5，但若使用指令python3，則會執行到3.8.2，也代表透過python3指令去執行時，使用的不見得是當下環境(app)的Library https://www…
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • 你執行時發生錯誤的環境是在 (base)，但提供conda list的環境是在(try)，還請在要使用的環境下(base)執行conda list，可透過conda deactivate退回到base環境
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • 請問一下，所使用的電腦是x64的ubuntu嗎? 另外，可否透過指令conda list，提供你現有環境下安裝的Lib與版本
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • The layer "sub" in your model is not supported in KL520, please use other layer to replace it. ( e.g. bn) And KL520 doesn't support "placeholder", either. I think it could be produced during framework transferring, please try to …
    in km.evaluate with 'InvalidProgramInput' Comment by Ethon Lin August 2021
  • In ISI mode, KL520 will load firmware and model from flash. So you must update fw and model before ISI inference. For example yolo, you can find firmware files in /app_binaries/KL520/tiny_yolo_v3/ and model in /input_models/KL520/tiny_yolo_v3/models…
    in python3 main.py -t KL520-cam_isi_async_yolo return -1 Comment by Ethon Lin August 2021
  • Hello，這個錯誤應該是因為kdp_host_api-x.x.x_linux_-py3-none-any.whl 與你的系統環境不相容所造成 為了要跟耐能加速棒(dongle)溝通，在各種作業系統下都需要編譯底層的驅動後才可正常運作。為了方便大家使用，我們在X64的環境下編譯了Windows與Linux的whl，在這兩種…
    in ImportError: No module named common Comment by Ethon Lin August 2021
  • 若是重新插拔以及在Windows環境下也是一樣的問題，那應該就是dongle本身有損壞需要進一步的分析，還請向電腦公會申請更換，聯絡方式如下 電腦公會的湯小姐 justine_tang@mail.tca.org.tw 02-2577-4249 #390
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • 請問，將dongle插拔後再試結果還是一樣嗎? 是否會有windows環境也可以試試看是否一樣的現象呢?
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • https://www.kneron.com/forum/discussion/comment/334#Comment_334 因為使用的是KL520的dongle，指令的部分還請加上 KL520，完整指令如下 python main.py -t KL520-update_fw https://www.kneron.com/forum/uploads/007/K60QV1S8SN6D.jpg
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • Hello, "add device failed" 表示電腦端透過host_lib這包程式跟dongle的溝通失敗了，所以無法做進一步的應用。因這樣的錯誤有很多可能性，所以想請你幫忙檢查下面的項目 dongle的購買來源是? 時間點大約為何時? 環境中是否有安裝libusb (apt install libusb-…
    in 更新韌體錯誤 Comment by Ethon Lin August 2021
  • The two models LittleNet.onnx and LittleNet_convert.onnx are different. That's why you got different result. The weight between this 2 models are different https://www.kneron.com/forum/uploads/066/8RJBHD6KBH4Y.png And the op-type of the last layers …
    in how to explain inference result of LittleNet example? Comment by Ethon Lin August 2021
  • Hi Denis, It means the operator deconvolution could be used in KL520 and our compiler will use upsampling + conv to implement the operator. So you don't need to do other operation with the layer deconvolution.
    in Deconvolution onnx sample Comment by Ethon Lin August 2021
  • As the photo below, the output of LittleNet.onnx is a array with dimension 2x1x1. And you will get different inference result with different image input. https://www.kneron.com/forum/uploads/538/971ACVSY3PQH.jpg If you want to run your own model, …
    in how to explain inference result of LittleNet example? Comment by Ethon Lin August 2021
  • https://www.kneron.com/forum/discussion/110/importerror-no-module-named-ktc The ktc module is a library of python, so you should use ktc module in python only. You can import it in your python file like "/workspace/examples/LittleNet/python_api…
    in ImportError: No module named ktc Comment by Ethon Lin August 2021
  • It's Cyclic redundancy check. The api is used for getting the CRC of model data, to make sure the data transportation is successful. You can find the information from our document center. http://doc.kneron.com/docs/#host_lib_1.0.0/kdp_host.h/#kdp_g…
    in What is kdp_get_crc's "CRC" stand for? Comment by Ethon Lin August 2021
  • Could you provide more specific information for clarifying the issue? Like what kind of commands you had used, which command makes you meet the error, and the full error message you encountered, etc.
    in failing to convert the onnx model to the nef file Comment by Ethon Lin July 2021
  • https://www.kneron.com/forum/discussion/comment/312#Comment_312 The control flow of NPU is "host_lib <-> scpu <-> npuc <-> NPU". And there are 2 ways to get inference with your image and model, "DME mode" and &…
    in How can I run the compiled *.bie and *.nef and get the hardware usage of the Kneron dongle? Comment by Ethon Lin July 2021
  • About your question: 1. Did you provide any API to get the AI Dongle's run-time hardware usage information?  What kind of information you want to get? You can find all corresponding APIs from following link. http://doc.kneron.com/docs/#host_lib_1.0.…
    in How can I run the compiled *.bie and *.nef and get the hardware usage of the Kneron dongle? Comment by Ethon Lin June 2021
  • Hello, As you mentioned the result of RGB565 was right but RGBA8888 (you bypass preprocess and implement by yourself) was wrong. I think the issue could be related to image format. Here is the format of RGB565, RGBA8888 and bypass preprocess https:/…
    in Same deep learning but different results between RGB565 and RGBA8888 Comment by Ethon Lin June 2021
  • The *.bie is a quantized model, you can run it on End to End Simulator. http://doc.kneron.com/docs/#toolchain/python_app/app_flow_manual/ And the *.nef is a model format for kneron dongle (KL520/ KL720), which was compiled from *.bie. To run inferen…
    in How can I run the compiled *.bie and *.nef and get the hardware usage of the Kneron dongle? Comment by Ethon Lin June 2021
  • Once run with out of memory, the system could keep on some memory issues still. Please exit from the docker environment, re-login and use 1 image case retry again.
    in Error when doing fpAnalyser Comment by Ethon Lin June 2021
  • Sorry but I don't understand your question. Could you show more details about your issue? Including the command you used, full error message, and so on. And it will be helpful if you could provide your onnx file. Did you successfully get the convert…
    in Test Model Problem Comment by Ethon Lin June 2021
  • Hi Raef, I think the issue was caused of the input dimension 1x12x160x160. Kneron's toolchain doesn't support 12-channel input and run image preprocess with 3 channels as default setting. That's why the error message showed got 76800 lines ( 3x160 …
    in Porting YOLOv5 Comment by Ethon Lin June 2021
  • Hi Angie, I checked your model and found out the issue is caused by the dimension 16x3x224x224. We see the first degree "16" as batch_size, and the KL520 / KL720 only support the case whose batch_size is 1. (e.g. 1x3x224x224) That's why …
    in fpAnalyserBatchCompile_520 raise error Comment by Ethon Lin May 2021
  • Hi Tim, Would you please provide the onnx or h5 for debug?
    in Error when attempting model editing (removing the softmax) Comment by Ethon Lin May 2021
  • Have ever checked the image you set in json? It seems there are some issues in model input. Input file dimension is not correct: expected: 2408448, but got: 150528 lines. /workspace/.tmp/input.1/ILSVRC2012_val_00000003.txt
    in fpAnalyserBatchCompile_520 raise error Comment by Ethon Lin May 2021

© Kneron, Inc.