林韋銘
林韋銘
About
- Username
- 林韋銘
- Joined
- Visits
- 36
- Last Active
- Roles
- Member
Comments
-
admin@rk3399:~/src/kneron_plus/python$ sudo bash install_libusb.sh root is not in the sudoers file. This incident will be reported. root is not in the sudoers file. This incident will be reported. I sure I have this file, and I already "chmo…
-
已經可以在Dongle上跑了，可是遇到一個狀況，我確定只是單純用這範例訓出來的模型會這樣，用預設PLUS的模型不會這樣。 問題就是，我用tutorial.ipynb的訓出來的模型執行到其中的這段之後 !python ../exporting/yolov5_export.py --data ../yolov5/data/pretrained_path…
-
https://www.kneron.com/forum/uploads/000/YXQ0OCMZWYFB.zip @Ethon Lin 這邊提供用toolchain轉換後的onnx跟nef
-
https://www.kneron.com/forum/uploads/865/BEW0LSDX5Y7O.zip 這是我toolchain量化的腳本
-
@Ethon Lin 請問一下 我已經找到之前你們模型的yolov5版本，我從官網的教學裡面的yolov5下去訓的，資料夾內inference.py 測試模型推論正常。 確實也可以經過docker toolchain量化完成，形成nef https://www.kneron.com/forum/uploads/040/WXJ84RE78S0U.png 可是現在…
-
https://www.kneron.com/forum/uploads/819/SVOS0Y3JJBKQ.png 對了，上面提供過的6.0版本yolov5s的output2.onnx 模型，我有嘗試調整最後一層的concat axis=1 變成 concat axis =-1， 然後現在錯誤變成這樣，好像還是像你說的reshape的關係，可是我要怎麼移除reshape層…
-
我訓練的是YOLOv5s的6.0版本，你貼的這串討論串上面寫說只支援2.0的版本～～～～～？ 因此我要不重新訓練舊版2.0的YOLOv5s，要不就研究6.0怎麼應用在KL720？ 可是剛剛我發現2.0的預訓練模型已經移除了...... 那這樣我先訓練YOLOv5s的5.0看看，看看是否能在KL720上推…
-
嗨，請問一下因為我是使用官方的yolov5s，不過我是看你們耐能文件上好像有支援yolov5s，所以看這狀況是不支援直接訓完的模型，還需要做修改嗎？！ 好奇你們之前遇到這狀況是怎解決？ 如resize, shape, reshape等都移除，然後推論結束後再到cpu上補做<========這流…
-
是的，我就是參考章節2.3才發這篇文的，因為看到有支援，可是跳出錯誤。 不好意思，我照片中的output2.onnx在這裡，我是使用toolchain裡面的指令 python /workspace/scripts/convert_model.py onnx /data1/yolov5s.onnx /data1/output2.onnx 這個跟你指的3.1.5是一樣…
-
https://www.kneron.com/forum/uploads/123/UE0C92MWFBCR.zip https://www.kneron.com/forum/uploads/663/4RM3D2A8QSVG.zip onnx模型跟權重在這裡
-
感謝解答，這部份解決了。 發現是anaconda問題，要先到原環境去安裝完整套件，就正常使用了，謝謝。
-
cam_isi_pre_post_host_fcos.py檔案執行會有錯誤這BUG要解決.... 因為我發現這檔案是會用KL720底層package的預處理API才錯， 但是我圖片沒經過預處理，丟到模型會有錯誤，這部份是否日後會有修正嗎？ 還是說這是SDK要更新嗎？ 可是我該如何更新，哪裡可以找到步驟呢？
-
我下載了，確實範例比較完整。 不過這個cam_isi_pre_post_host_fcos.py檔案執行會有錯誤 https://www.kneron.com/forum/uploads/945/DRGWW22BZND9.png 其他的正常，因此我可能會從這兩個，改成我要的dongle視訊串流 yolo_public_example.py cam_isi_post_host_yolov3_s…
-
https://www.kneron.com/forum/discussion/comment/215#Comment_215 Hello, I can't find "KL720 HDK". Where is it.
-
Hi all, I already follow YOLOv3 step to step, I have onnx and bie and nef, I used the last method about inference three model onnx / bie / nef. My onnx inference has data, but my bie always Segmentation fault (core dumped). My nef always stops, ca…
-
Hi, I tried that agin, I sure already to use correct 2 nodes, however it still fail. It maybe is nomalize problem? Or model converting fail problem? image / 127.5 -1 https://www.kneron.com/forum/uploads/778/HKTSLL8ZICVZ.png image / 255 https://www…
-
https://www.kneron.com/forum/uploads/007/DH7PAFU7MDOC.png Hi, I tried the 2 of 3 nodes output, however it become this. It maybe is nomalize problem? I already try image / 255 or image / 127.5 -1. It's still fail. Or it's model converting fail proble…
-
Sorry, I don't understand your mean. Because I can't get three node output. How can I send varialbes to parse_objects parse_objects(cmap, paf)?
-
Hello, The following is my pose estimation local code. How to fix about kneron_inference ? https://www.kneron.com/forum/uploads/076/KD5S1GABJEJ7.png It's my code, but its error. https://www.kneron.com/forum/uploads/126/DM2JALG97XVH.png https://www.…
-
I ref python-api document to inference. It's correct methods? If it can inference, I continue to solve firmware and hardware problem? The following is my problem. after Inference, how to get result? https://www.kneron.com/forum/uploads/557/AGRSJNOV…
-
Your forum always eat my messages.................................................................................. Many times............................. ================================================================================ python /wor…
-
The following is my model format. https://www.kneron.com/forum/uploads/992/ZOVVOZKU0GDJ.png I used toolchain about 0.14.0 verssion. The following is my command and output. (base) root@06a381b7a23f:/workspace# python /workspace/scripts/convert_model…
-
I used onnx model for converting, it appear the problem. pytorch 1.7.1 onnx 1.4.1 onnxruntime 1.6.0 Traceback (most recent call last): File "onnx2onnx.py", line 55, in <module> m = combo.preprocess(m, …