
Maria Chen
Maria Chen
About
- Username
- Maria Chen
- Joined
- Visits
- 1,092
- Last Active
- Roles
- Member, ModeratorsKL520, ModeratorsKL720, ModeratorsAIModel
Comments
-
您好, kp.GenericInageInferenceDescriptor是Kneron PLUS v.2.0用的,所以您可以用Kneron PLUS v1.3.0的kp.GenericRawImageHeader喔。 這裡有兩個版本的API對照表: V1.x and V2 APIs Mapping Table - Document Center (kneron.com) https://www.kneron.com/forum/uplo…
-
您好, for filename, gt_label in samples: ValueError: not enough values to unpack (expected 2, got 1) 有可能是因為samples中,沒有分別拿到filename與gt_label (如下圖) https://www.kneron.com/forum/uploads/002/T1JIUF8T92C2.png 有兩種dataset格式符合架構…
-
您好, -Can't open file 'tools/deployment/pytorch2onnx.py' No such file or directory: 您可以在跑程式前,先用Colab的files view找到檔案,再用copy path複製路徑。Colab的路徑,與使用者mount的Google Drive資料夾相關,這個部分可以在網路上找到相關說明。 -Key…
-
Hi, 這個問題如果在docker那邊問,可能會有比較好的答案,但是您可以試著跑跑看docker image prune,這會刪除沒有在用的container。或是docker rmi $(docker images -q --filter "dangling=true"),這會移除dangling images。 或者您可以確認當初安裝raspber…
-
您好, 您提到的project (host_lib)裡面也有postprocessing。dme_inference裡面會呼叫dme_get_result,在那裡面會拿raw output (feature map)去做postprocessing: https://www.kneron.com/forum/uploads/881/E2Q5VG38ZZUB.png Host_lib裡的postprocessing範例在host_lib…
-
Hi Johnson, 謝謝您提供的資訊! 我們看了您提供的程式。 在KL520上,需要先跑load_model_from_file (下面被註解掉的地方),才能跑get_model_info,因為usb-boot upload fw會洗掉DDR上的所有資料(包含模型)。 https://www.kneron.com/forum/uploads/331/7ZP6BG0LFYKB.pn…
-
Hi Johnson, 可以跟您請教一下您的OS版本嗎 (Windows, Linux, etc.)? 還有,您的KL520的USB加速棒是如何與您的電腦連接的呢? 您的電腦現在有連接著很多其他的東西嗎? 因為load model時會再次與KL520加速棒連接,這時如果連接速度太慢,有可能會造成這個error。 P.S. …
-
Hi, 在執行gereric inference時不需要加sudo,因為在python環境中用sudo的話會跑到另外一個環境,可能就不是您安裝的環境了。 若是沒有用sudo會遇到USB權限問題,請參考文件說明設定使用權限: Install Dependency - Document Center (kneron.com)
-
Hi Su, Tutorial在docker裡面,需要先安裝docker,這個文檔有安裝方式與連結: Toolchain Manual - Document Center (kneron.com) Docker的用法: http://doc.kneron.com/docs/#toolchain/manual/#2-toolchain-docker-overview Tutorial資料夾在docker裡的位置是: /works…
-
Hi Richard, Error 111 是 KP_FW_INVALID_PRE_PROC_MODEL_INPUT_SIZE_111,當preprocessing的input size不符合規範的時候會有這個error。 因為像您所說的,2112比1023大,所以會有error。這部分是KL720目前inproc (hardware preprocess) 的限制,目前超過的話可以透過b…
-
Hi Gopinath, No problem! I don't think there is. The examples for AI SoC Development Kit only uses the Tiny Yolo V3 model. What you could do is use Kneron PLUS' Generic Inference example in Python to inference with your own model: Run Examples - Doc…
-
Hi Jack, 謝謝您提供的結果! 我們的同事有再調整一下您的 code ,趨近您理想的結果。 https://www.kneron.com/forum/uploads/477/RJLX9NHDGV2K.zip 數據不同的原因主要是您的inference header要送的buffer size沒有填正確 (原本送的是沒有alined過的data size) 名字裡…
-
Hi Jack, 這是我們同事跑出來的數據,請問一下這個有符合您預期的結果嗎? https://www.kneron.com/forum/uploads/690/N2BCPSF2V8FU.txt
-
Hi Jack, 第一個問題(module 'kp' has no attribute 'v1'),是因為版本不同(v1.3.0/v2.0.0),所以需要再改程式裡的一些地方才能成功地跑。 第二個問題,轉成float的動作是只要用bypass_preprocess,都會需要去做。 下面的圖,Data Inference的地方有幾個步驟: https://…
-
Hi Jack, 要inference之前,我們會把float (32 bits)去做浮點到定點(8-bit fixed point)的轉換來量化: https://www.kneron.com/forum/uploads/531/VG6DDPP878BD.png 然後這裡(上面回覆的連結)有說明要如何排列資料,您的layout會需要用KP_MODEL_TENSOR_DATA_LAYOUT_1W1…
-
Hi Jack, There's also an example talking about inferencing none image data without built-in hardware image pre-processing here: Data Inference - Document Center (kneron.com) I hope this helps.
-
您好: 不好意思,我不太清楚義晶的板子,可能需要請您詢問義晶的人員或是販賣這個AI BOX給您的人幫您處理了。
-
Hi Gopinath, Are you talking about the KL520 series AI SoC Developement Kit? If so, there is an Assembly Instruction inside. The board should be set up like the photo below. If this wasn't what you were asking about, please let us know what KL520 S…
-
Hi Jack, Sorry for the confusion, I'll try my best to explain this. Since you're bypassing the preprocess, you could convert your frames into an array first. Then, you would need to know your model's normalization, and write a function that converts…
-
Hi Gopinath, I'm glad I could help! And sure, you could download Kneron PLUS from here Developers | Kneron – Full Stack Edge AI to do inferencing with your camera on your laptop, or with a USB camera connected to your computer. If you use C, you co…
-
您好, 謝謝您的回饋,很高興程式可以執行成功!
-
您好, 可以請您確認一下這些嗎? 謝謝! -您的Python版本 (app_face_detection_recognize支援Python 3.5-3.9) https://www.kneron.com/forum/uploads/414/BY1SGFW7YSWZ.png -您的firmware版本(Firmware需要KDP2,如果不是的話需要更新) https://www.kneron.com/forum/u…
-
Hi Gopinath, Thank you for answering the questions. So even if you clicked the Options tab -> List All Devices in Zadig, it wouldn't come up as "Kneron KL520"? Is the USB dongle detected in your Device Manager? https://www.kneron.com/f…
-
Hi Gopinath, Could you specify what OS you're using? If you were using Windows, you would need to install Zadig, and if you were using Ubuntu/Raspberry Pi, you would need to configure USB permission. For more information in regards to installing, yo…
-
Hi Jack, Our pre-processing only works for 4W4C8B format, so you would need to use kp_generic_raw_inference_bypass_pre_proc_send (for Kneron PLUS v1.3.0) or kp_generic_data_inference_send (for Kneron PLUS v2.0.0) to directly send the data for infere…
-
Hi Jack, To inference a non-image format: If you were using Kneron PLUS v1.3.0, you could use the function kp_generic_raw_inference_bypass_pre_proc_send to bypass the pre-processing and inference your input. You would also need to be aware of the NP…
-
Hi Jack, Are you using the examples in the example_xxx folders (e.g. example_kdrv and example_sbt) in the firmware/build folder? If so, our examples can only use J-Link to load the firmware to DDR right now unless you modified them, since they're ju…
-
您好: 這個裡面,有附一些keil MDK的網站: v1.5.x - Document Center (kneron.com),也有keil的文檔連結可以參考。 價錢的話,這裡有寫: Compare MDK Editions (keil.com),我們建議使用者購買essential version即可。
-
https://www.kneron.com/forum/discussion/comment/1129#Comment_1129 Hi Karasu, Yes, we could have a non-image format as the input. If you were using Kneron PLUS v1.3.0, you could use the function kp_generic_raw_inference_bypass_pre_proc_send to bypa…
-
您好: 問題一: 不好意思,我看到您的圖片裡是有看到有執行下面的command,不過不確定有沒有漏掉exporting前面的../ (然後確認這個yolov5資料夾的外面有exporting資料夾,裡面應該要有yolov5_export.py) https://www.kneron.com/forum/uploads/156/U78H58S1GLJY.png Def…