Maria Chen
Maria Chen
About
- Username
- Maria Chen
- Joined
- Visits
- 649
- Last Active
- Roles
- Member, ModeratorsKL520, ModeratorsKL720, ModeratorsAIModel
Comments
-
Hi Haresh, When there are multiple models, you could combine them into one nef file by using ktc.combine_nef: 5. Compilation - Document Center (kneron.com) There is a demo app "kl720_demo_customize_inf_multiple_models" for multiple models …
-
Hi, For now, KL630 is only available through sales channels and it's not publicly available yet. To get permissions on the Kneron website, please contact our sales team: brian.lin@kneron.us for assistance. Thanks!
-
Hi JungTae, For now, KL630 is only available through sales channels and it's not publicly available yet. Please contact our sales team: brian.lin@kneron.us to get permissions. Thanks!
-
Hi Youngjun, We don't have access to your onnx model, but according to the model structure you provided, you will need to use onnx2onnx to convert your onnx model to a Kneron-supported onnx model first, then proceed with converting. Below is an exa…
-
Hi Haresh, Thank you for explaining how you processed your model. We've checked the onnx2onnx.onnx file, and it seems like the operators mentioned above are still there. As we have recommended you earlier, even if the operators Reshape and Concat an…
-
Hi Youngjun, Our Kneron toolchain supports onnx opset 11 and 12, so you'll need to make sure all the operators match opset 11 or 12. According to your onnx model structure, there are Hardswish nodes in the onnx model here and there, so we can't cut …
-
Hi JungTae, Could you check if you've installed the dependencies on your Ubuntu? Thanks! Please refer to: Install Dependency - Document Center (kneron.com)
-
Hi Haresh, Our model team checked your model, and we would recommend you to try cutting the Reshape and Concat operators and moving them to post processing even though they're supported by KL720. If that doesn't work, please cut the Transpose operat…
-
Hi Haresh, Sorry for the late reply. Just in case, please check that you have gone through the following steps: Use onnx-simplifier to simplify your original onnx model (Note: not the optimized one) Run onnx2onnx Since there are nodes that aren't su…
-
Hi Youngjun, Have you converted your onnx file to onnx format supported by using onnx2onnx_flow in the toolchain? https://www.kneron.com/forum/uploads/155/XYE8J7WCGC15.png The model is supported as long as the operators are supported by KL630: Hardw…
-
Hi Youngjun, Your error message says: ERROR:root:Analysis is required before compile. The error is showing up because you didn't use km.analysis before you use km.compile. Please refer to this part in the documentation center on how to convert an on…
-
Hi Youngjun, Sorry for the late reply. Docker toolchain and Movinet are different, but you don't have to convert your model to onnx with a 3rd party tool inside docker toolchain. You could convert it inside your own environment, then put the onnx in…
-
Hi Son Nguyen, Sorry, we do not have a support list for Wi-Fi modules or chips. If you wish to implement a Wi-Fi solution on the KL720, additional support from Kneron will be required. Please send an email to our sales leader, brian.lin@kneron.us, d…
-
Hi Son, I've attached a document on power consumption for your reference: https://www.kneron.com/forum/uploads/729/3WBW0WR8BEZ9.pdf Flash support list: https://www.kneron.com/forum/uploads/974/QSG74IFTN0EJ.png Unfortunately, we don't have one for wi…
-
Hi, For now, KL630 is only available through sales channels and it's not publicly available yet. Please contact Nick Wang (nick.wang@kneron.us) and FanChiang (shihchun.fanchiang@kneron.us) for technical assistance. Update (April 23): Our team membe…
-
[This is a duplicate of the following question: KneronDFUT-Ubuntu can only be run on Ubuntu 18.04 — Kneron Developer Forums]
-
Hi Yuchen, Unfortunately, we can't remove the version check. If you are using a version that's not 18.04, you could build your own DFUT console instead of using the pre-built DFUT GUI. Step1: Download the latest PLUS here: https://www.kneron.com/tw…
-
Hi Youngjun, Yes, you could try converting the keras model to onnx with keras2onnx. There's also tensorflow-onnx that you could use if you could convert the keras model to tf: https://github.com/onnx/tensorflow-onnx
-
Hi Youngjun, We would recommend you to convert the hdf5 file into an onnx file by using a third-party program instead of keras2onnx, then continue the nef conversion flow with that onnx file.
-
[This is a duplicate of the question here: I encountered an error while trying to convert a bie file to a nef file. — Kneron Developer Forums]
-
Hi Haresh, Our model team checked your script, and it looks okay. Before converting your model, we would suggest you to follow these steps: Use onnx-simplifier to simplify your original onnx model (Note: not the optimized one) Run onnx2onnx Since th…
-
Hi Haresh, Sorry for the late reply. Could you provide us with your script for converting the onnx to nef as well? Thanks! The onnx model you've attached (effdet_kneron_ops.onnx) seems like it hasn't been optimized yet: https://www.kneron.com/forum/…
-
Hi JungTae, Sorry for the late reply. The error message "Input onnx is missing" means that your input is missing the onnx file. Please make sure you're including an onnx file as an input. Thank you for providing the onnx files. This might…
-
Hi Haresh, For questions on KL630, please send another email to Nick Wang for assistance. Thanks!
-
Hi Haresh, The error you got is "ApiReturnCode.KP_ERROR_INVALID_PARAM_12," which means you did not fill out kp.GenericInputNodeImage correctly. Please refer to the right part of the code (KL720DemoGenericImageInference.py) https://www.kner…
-
Hi JungTae, Could you provide us with your results for your IP Evaluator and all of your files, including your onnx file? If all the previous steps worked smoothly, this might be a compiler issue. Thank you!
-
您好, 燒錄時,UART的畫面會有kmdw_dfu_update_model: flashing,這個代表有在燒錄: https://www.kneron.com/forum/uploads/210/889H55BFV2AU.png 但是之後會有選擇BOOT MODE的畫面,如果很長的時間沒有選擇SPI-NAND的話,就會有Error code: 28 https://www.kneron.co…
-
您好, 除此之外,您也可以用Boot mode: Manual (UART) 和 flash_programmer.py來燒錄: Flash Management - Document Center (kneron.com) 關於mode的資訊: Flash Management - Document Center (kneron.com) 關於USB boot和Flash boot: Upgrade AI Device To KDP2 - D…
-
您好, 您可以用UART來查看您的BOOT MODE是什麼。 當KL720開發板在BOOT MODE: USB的時候,會有您看到的error: https://www.kneron.com/forum/uploads/922/IQCKKFCRAAC1.png https://www.kneron.com/forum/uploads/634/J42E54O7GSAR.png 在BOOT MODE: SPI-NAND的時候,…
-
Hi Haresh, The error says, "Input name does not match," with the onnx input ({input_nodes}) and given np ({input_np.keys()}), so you might want to make sure that the order of the names are matching the order of inputs in pre_results: https…