Default Avatar

Maria Chen

Maria Chen

About

Username
Maria Chen
Joined
Visits
1,066
Last Active
Roles
Member, ModeratorsKL520, ModeratorsKL720, ModeratorsAIModel

Comments

  • Hi Olivier, The memory size restriction for KL720 is 70-75MB. Reference: Write Model To Flash - Document Center https://www.kneron.com/forum/uploads/887/80S281ZRN3EO.png Our sales representative's email is: brian.lin@kneron.us You may also use our w…
    in Voice inference with KL720 Comment by Maria Chen April 28
  • Hi Olivier, As long as the onnx model's operators are supported by KL720, it should be able to run. Supported operators list: Hardware Supported Operators - Document Center For a reference design for the chip, please contact our sales team. They wou…
    in Voice inference with KL720 Comment by Maria Chen April 25
  • Hi Jyoti, Usually, those who port their models would write their own postprocess, as they are the most familiar with their model. There are example tiny yolov3 and yolov5 postprocess functions in kneron_plus/python/example/utils, and for further tec…
    in Yolov8 output Data dumping in KL630 Comment by Maria Chen April 22
  • 您好， 那個文檔用的toolchain是比較舊的版本。用最新的toolchain版本修改模型的話，如果opset是11或12，可以在base環境使用ONNX editor。如果是opset 13到18，可以在onnx1.13環境使用onnx.utils.extract_model (https://onnx.ai/onnx/api/utils.html)。
    in Kneron AI-KL730 Comment by Maria Chen March 28
  • 您好， https://www.kneron.com/forum/discussion/comment/2259#Comment_2259 用onnx_convertor轉換工具來轉換pytorch等的模型成onnx，應該是可行的: 3. Floating-Point Model Preparation - Document Center 如果會失敗的話，可以試著在Kneron Toolchain (docker)裡…
    in Kneron AI-KL730 Comment by Maria Chen March 26
  • 您好， https://www.kneron.com/forum/discussion/comment/2258#Comment_2258 關於這些問題: 1 問題是因為toolchain轉換的過程會自動將input format設定成1W16C8B，所以pytorch2onnx_kneron.py不用修改喔。 2 現在，因為firmware的preprocess有出現問題，所以pre_proc_…
    in Kneron AI-KL730 Comment by Maria Chen March 26
  • 您好， 不好意思，我們找到原因了! 因為在Kneron Toolchain轉換模型時，會自動將input format設定成1W16C8B，所以您的model input format是1W16C8B: https://www.kneron.com/forum/uploads/498/X4BBLC6WKTNV.png 一般的input format是4W4C8B，而1W16C8B也可以支援，但…
    in Kneron AI-KL730 Comment by Maria Chen March 26
  • 您好， 回答您最新的問題: 雖然nef model看起來沒有問題，但是KL730 generic inference應該要可以跑，但是會失敗。 YoloX當時是給KL720的範例，而且是Kneron PLUS 1.x的時候的文檔，目前沒有人在維護，那時候還沒有KL730。現在的Pytorch版本也一直在更新，導致model架…
    in Kneron AI-KL730 Comment by Maria Chen March 26
  • 您好， 我也有轉換您的onnx模型，雖然可以成功轉換成nef模型，跑KL730 generic inference卻也會失敗 (這個generic inference，用任何nef模型應該都要成功)。我認為可能是因為您之前說過的"编译出来的YOLOX模型与创建KL730单一模型示例图像格式不匹配"，因為…
    in Kneron AI-KL730 Comment by Maria Chen March 25
  • Hi Jyoti, If you were talking about how in Kneron PLUS Python, the numpy arrays get truncated when you print out the results, you could try using: import sys import numpy numpy.set_printoptions(threshold=sys.maxsize) This would help print out all th…
    in Yolov8 output Data dumping in KL630 Comment by Maria Chen March 25
  • 您好， kneron_inference的結果會是numpy arrays，所以會需要您寫模型的postprocess來得到座標之後，才可以用顯示邊界框(display)的function，function的細節在/workspace/E2E_Simulator/python_flow/utils/utils.py裡面: https://www.kneron.com/forum/uploads/124/9W…
    in Kneron End to End Simulator v0.28.0 Comment by Maria Chen March 21
  • 您好， 不好意思回覆晚了，因為error code -7可能源於各種原因，我們會需要先確認模型沒有問題，然後再復現error和確認code，可以請您提供以下的資訊嗎? 謝謝您! -NEF model -Onnx model (確認有沒有不支持的operators) -firmware.tar -Kneron PLUS的code 如果是用自…
    in Kneron AI-KL730 Comment by Maria Chen March 21
  • 您好， 因為KL720不支援那些運算子，所以可能會需要請您用其他的模型。 如果這些運算子是在模型的最後面，也是可以將它們剪掉之後再自行寫postprocess把剪掉的運算子加回去，不過我們會建議用其他的模型。 Toolchain的話，請用最新的v0.28.0來轉換模型。您可以使用這個…
    in 人體骨架偵測模型問題 Comment by Maria Chen March 12
  • 您好， 只要KL720有支援ViT架構的onnx模型中的operators，照理說應該可以跑。請參照文檔裡的清單: Hardware Supported Operators - Document Center
    in ViT架構可以放進KL720嗎? Comment by Maria Chen March 5
  • Hi Franklin, I'm sorry for their lack of communication. Could you contact Jeffrey (jeffrey-yc.chen@kneron.us) instead and cc Brian just in case? Thank you!
    in Kneron toolchain not converting the YOLOv5s to KL520 Comment by Maria Chen February 26
  • 您好， 不好意思，這個文檔已不支援，所以不會再有新的文檔了。訓練出來的模型的operators，只要是KL730都有支持，就可以用Kneron Toolchain轉換成.nef模型。請參照: Hardware Supported Operators - Document Center 轉換的nef模型就可以在KL730上進行推論。
    in KL730 Kneron ModelZoo Comment by Maria Chen February 25
  • 您好， 這個文檔現在已不支援，需要麻煩您用之前的mmcv版本，要與您的CUDA版本對應。下載的command是: pip install mmcv-full==1.5.0 -f https://download.openmmlab.com/mmcv/dist/{cu_version}/{torch_version}/index.html 如下圖，不過是用mmcv-full，mmcv版本為1.…
    in KL730 Kneron ModelZoo Comment by Maria Chen February 24
  • Hi Franklin, Yes, you should reach out to Brian (brian.lin@kneron.us), our sales representative. Thank you for your interest! You could also fill out the form on our website: Contact us | Kneron – Full Stack Edge AI
    in Kneron toolchain not converting the YOLOv5s to KL520 Comment by Maria Chen February 21
  • Hi Nhleem, Edit: We've answered your question in another email.
    in Any linear algebra libraries available/tested on KL630? Comment by Maria Chen February 21
  • 您好， 無論是使用任何模型，我們都會建議您使用最新的Toolchain (v0.28.0)和SDK (v2.2.0) 版本。 KL720 SDK在官網上可以下載，而Kneron Toolchain可以用"docker pull kneron/toolchain:latest"指令來進行更新。
    in 人體骨架偵測模型問題 Comment by Maria Chen February 17
  • 您好， 不好意思這麼晚回覆，感謝您的分享! 另外，我們的toolchain版本有更新，可以支持Opset 18: Kneronnxopt - Document Center https://www.kneron.com/forum/uploads/313/1K6MGYK85OYU.png 也可以參考我們支持的operators/nodes: Hardware Supported Operators - D…
    in yolov5s.pt 部署流程經驗分享 Comment by Maria Chen February 14
  • 您好， 不好意思這麼晚回覆。 1. 照理說可以，請在使用前確認KL730是否都有支援您的模型的operators: Hardware Supported Operators - Document Center 2 我們建議剪掉onnx模型中Concat以下的operators: https://www.kneron.com/forum/uploads/227/YPDF2CSNW4O9.png 剪…
    in 關於Pose model的問題？ Comment by Maria Chen February 14
  • Hi again Franklin, For KL520 hardware information, you could refer to these documents available on our Developer Center: Developers | Kneron – Full Stack Edge AI https://www.kneron.com/forum/uploads/525/ZYX6GRBR8MVC.png
    in Kneron toolchain not converting the YOLOv5s to KL520 Comment by Maria Chen February 13
  • 您好， 是的，無論是用USB上傳和firmware燒錄都會需要先用NEF Combine組合兩個nef模型，然後再做燒錄喔。 NEF Combine的說明: 5. Compilation - Document Center 在KL720上用多個模型的範例: Create Multiple Model Example for KL720 - Document Center
    in KL720雙模型 Comment by Maria Chen February 13
  • 您好， 我們沒有特別建議使用哪一個架構，只要模型的operators都是KL720有支援的話，照理上都可以使用喔。 硬體支援的operators: Hardware Supported Operators - Document Center 也可以參考Kneron硬體的效能: Hardware Performance - Document Center 使用Kneron Too…
    in 人體骨架偵測模型問題 Comment by Maria Chen February 12
  • 您好， 可以的，如果是要用USB上傳模型，大小的限制總共是75MB，而如果是在firmware上燒模型，限制總共是70MB。 https://www.kneron.com/forum/uploads/635/CQL637KGXO9U.png 參考文檔: Write Model To Flash - Document Center
    in KL720雙模型 Comment by Maria Chen February 12
  • Hi Franklin, These are the platforms you can build and run Kneron PLUS on: https://www.kneron.com/forum/uploads/135/4K7XP5J1COMK.png If you are not using the above platforms, to flash the KL520 firmware, you could download Kneron PLUS and try buildi…
    in Kneron toolchain not converting the YOLOv5s to KL520 Comment by Maria Chen February 11
  • Hi SeonGyun, In that case, I don't think it's possible.
    in How to cross-compile ONNX Runtime and OpenCV and deploy them on kl630? Comment by Maria Chen February 10
  • Hi SeonGyun, Unfortunately, we can't run OpenCV and ONNX Runtime directly inside KL630, but if you were talking about running OpenCV on host side when KL630 is in companion mode, it is possible. Please refer to this link for reference: Create Single…
    in How to cross-compile ONNX Runtime and OpenCV and deploy them on kl630? Comment by Maria Chen February 10
  • Hi, The nodes labeled as "cpu_nodes" are nodes that are not supported by KL520 NPU: kdp520/ip_eval/cpu_node: Sigmoid: Sigmoid_129, Sigmoid_131, Sigmoid_133 Since KL520 doesn't support Sigmoid nodes, you will need to cut them in your onnx m…
    in Kneron toolchain not converting the YOLOv5s to KL520 Comment by Maria Chen February 10

© Kneron, Inc.