Phidias
Phidias
About
- Username
- Phidias
- Joined
- Visits
- 56
- Last Active
- Roles
- Member
Comments
-
I used /workspace/libs/ONNX_Convertor/optimizer_scripts/onnx2onnx.py to optimize the model, and in my case the optimize script cut out Softmax after Gemm op already (and add an add nop as the output): https://www.kneron.com/forum/uploads/167/2MT…
-
I've changed the format constants to 0x0d , the results changed but still are far from accurate. The accuracy is less than 20%. I've also test with and without CHANGE_ASPECT_RATIO flag and I think that's not the problem because our the size of imag…
-
For img_preprocess_method, I use default values in toolchain manual: "preprocess": { "img_preprocess_method": "kneron", "img_channel": "RGB", "radix": 8, …
-
I've put training data when optimizing the model, and changed from NPU_FORMAT_RGB565 to NPU_FORMAT_RGBA8888 , and convert the color space when loading image respectively (img = cv2.cvtColor(img, cv2.COLOR_BGR2RGBA)) , the results changed but still…
-
Thanks for the help, we can now retrieve the data and do some post process. However the result is far from our original model, and our data scientist is wondering that if the image converting (such as BGR2BGR565 ) necessary for KL520 dongle. If it i…
-
I must misread the API at some point, now I can retrieve inference result, thanks for the help! However I still have an additional question. With the above test model, the shape of output layer is `float32[1, 3]`, which I presume should provides 4 x…
-
https://www.kneron.com/forum/uploads/503/4DB81J2VCPA8.zip This archive contains a original test model and converted firmware binary we provided in another thread (Warnings when running `fpAnalyserCompilerIpevaluator_520.py` — Kneron Developer Forums…
-
Hi, I've run update_fw and regenerate the model with correct model_id (1000), but I still got no result, data in inf_res buffer are all zeros. As far as I know, since we're using a classification model (instead of detection), it should still produ…
-
Good to hear that, thank you for the support!
-
https://www.kneron.com/forum/uploads/874/V1DDBDVJXJ5U.zip This result was generated by using the testing model uploaded earlier, please have a look, thank you in advance!
-
Thanks for the help! This time I use command: tflite_convert --graph_def_file=output_graph.pb \ --output_format=TFLITE \ --output_file=char_mobilenet_1.0_128_20180515_unquant.tflite \ --input_arrays=input…
-
https://www.kneron.com/forum/uploads/596/10EQE6FK2OWL.zip The zip file contains: output_graph.pb : The original Tensorflow frozen graph test_mobilenet_1.0_128.tflite : The TFLite version convert from frozen graph with command: tflite_convert \ --g…
-
Thanks for the reply! I've migrate to v0.8 (because v0.9 doesn't have python bindings), and I still got no result. By the way, the host_lib download link in KL520 - Document Center (kneron.com) is still v0.4. The only change I made is to add additio…
-
Related issue: Warnings when running `fpAnalyserCompilerIpevaluator_520.py` — Kneron Developer Forums