洪承孝
洪承孝
About
- Username
- 洪承孝
- Joined
- Visits
- 155
- Last Active
- Roles
- Member
Comments
-
https://www.kneron.com/forum/discussion/comment/117#Comment_117 Hi, @Raef Youssef Because I tried multiple scripts to convert ONNX file, but they always compiler fail after use "batchcompilerfpAnalysis.py" So, I just according to my succe…
-
https://www.kneron.com/forum/discussion/comment/115#Comment_115 Hi, I'm really sure this model from PyTorch does not work for me. Could you re-train to generate the weights file? Because I will convert to Keras format and then do the next step. For …
-
https://www.kneron.com/forum/discussion/comment/113#Comment_113 Could you give orginal model and some image? (*weights file)
-
https://www.kneron.com/forum/discussion/comment/110#Comment_110 I'm also changing "kneron" to "yolo", they still work.
-
I still have another problem that needs to solve. Just like "coco dataset + my own dataset". Although the successful compiler and detection, the results were very strange. For example, my dataset is fire and smoke. When I input an airplane…
-
https://www.kneron.com/forum/discussion/comment/108#Comment_108 Sure, I will show you my input_params.json content. I'm using 224x224 models because I can not compiler success in 416 or 608 sizes. { "model_info": { "input_…
-
You can reference my final convert results. I didn't edit any node removal, but success all convert steps. Remark: No matter what I use to convert(Ex:pytorch2onnx、tensorflow2onnx) only "keras2onnx" successful. https://www.kneron.com/forum…
-
https://www.kneron.com/forum/discussion/49/porting-tiny-yolov3-example I think this is a bug in "tensorflow2onnx" and "pytorch2onnx". When I try to use "weights" convert to Keras format(.*h5) before converting to ONNX,…
-
https://www.kneron.com/forum/discussion/comment/104#Comment_104 It doesn't work for me. Could you share yolov3 convert steps? Thanks.
-
This is my output after "fpAnalyserCompilerIpevaluator_520.py" input = /workspace/.tmp/updater.json Traceback (most recent call last): File "/workspace/scripts/fpAnalyserCompilerIpevaluator_520.py", line 43, in <module> …
-
This is my original model after generated from the weights file. https://www.kneron.com/forum/uploads/967/C8F0OT3SBRAE.7z
-
https://www.kneron.com/forum/discussion/comment/99#Comment_99 I trying to do this, but not work. My model is onnx when it generated by weights file. And then do onnx2onnx to convert model.
-
@Jiyuan Liu Hi, I also have same issue, could you help me to check my model before running onnx2onnx?
-
By the way, my output model is no upsample node. Because I can not bypass to fpAnalysiscompiler when I keep this node. So, I'm not sure this operation relates to the accuracy.
-
https://www.kneron.com/forum/discussion/comment/93#Comment_93 @kidd HI, Where could I found to set threshold value or you mean detection threshold? Both of them were set "0.1f" to detect.
-
https://www.kneron.com/forum/discussion/comment/81#Comment_81 I think this problem was solved. Because I change to use PyTorch to generate Onnx file and do convertor in the toolchain. So, input size will be normal after convert. But I still have som…
-
https://www.kneron.com/forum/uploads/508/GUUB6CBOJU22.rar This is my original PB file, could you help to check my convert problem? Thanks.
-
By the way, I used the ONNX file is convert by "tensorflow2onnx". Before I do it, the output shows me some error log, but I still can get the ONNX output. I'm not sure it may cause a problem? https://www.kneron.com/forum/uploads/343/9G51G7…
-
https://www.kneron.com/forum/discussion/comment/80#Comment_80 Hi, I'm trying to do this, but it seems like the same problem for me. https://www.kneron.com/forum/uploads/925/P3X63K9HFBIY.png https://www.kneron.com/forum/uploads/117/86W5WJIMFMDE.png …