Default Avatar

Jack Huang

Jack Huang

About

Username
Jack Huang
Joined
Visits
110
Last Active
Roles
Member

Comments

  • Hi Andy, 使用keras2onnx轉model成ONNX format, 出現如下錯誤訊息, 是否kneron/toolchain Docker環境下, keras2onnx不support Bidirectional?   onnx_model = keras2onnx.convert_keras( model, model.name )  File "/workspace/miniconda/lib/python3.7/site-pac…
    in Converting Keras with TimeDistributed layer to ONNX failed Comment by Jack Huang August 2022
  • Hi Maria, 謝謝您的幫忙, 這就是我要的結果. 瞭解怎麼轉換float data Thanks!!
    in Inference with not image data Comment by Jack Huang August 2022
  • Hi Maria, 跑出來的數據(result.txt)還是跟ktc跑出來的(as attached ktc_result.txt)有些差距, 應該會有很多frames有TRI的結果, ex. no.51~62, predict[1]值大於0.5. 不過, 我用修改過的跑出來的結果跟你們跑出來的數據不同, 會跟KL720內的SCPU F/W有關嗎? 我是load Kn…
    in Inference with not image data Comment by Jack Huang August 2022
  • Hi Maria, 從餵進model前的前置處理動作看來, 是把維度(27, 29, 3)的float轉成(27, 29, 16)的int8, 然後float值乘128 這樣的話, 我的model是否需要依照這樣的轉換修改train model的test data來重train? 因為原model依照這樣的轉換, 得到的結果都是(0.9921875, 0.007812…
    in Inference with not image data Comment by Jack Huang August 2022
  • Hi Maria, 取得model input radix/scale, input data layout and input size等相關資料時, 出現下列錯誤訊息, (AttributeError: module 'kp' has no attribute 'v1' &) AttributeError: 'SingleModelDescriptor' object has no attribute 'input_nodes' 是否是我的…
    in Inference with not image data Comment by Jack Huang August 2022
  • Hi Maria, NPU data layout format, 就我認知, 它應該是以byte(8Bits)為單位來處理input data, 若原始data是3個channel, 要丟進1W16C8B input format的model, 4th channel就要塞0; 而現在要丟進model的data卻是float(32 bits)的資料型態, 要如何做前置處理來符合model…
    in Inference with not image data Comment by Jack Huang August 2022
  • Hi Maria, For the NPU data layout format, it's hard to understand to me. Do you have some example to explain how to arrange this kind of format? For the input data of the model, a frame has 3 channels, and its row and column denote distance and spee…
    in Inference with not image data Comment by Jack Huang July 2022
  • Hi Maria, If my model is as the below format, the input data are the set of 4 bytes of float data w/ dimension 27x29x3, liked as width 29, height 27 & channel 3 https://www.kneron.com/forum/uploads/052/71RB0YYQTU18.png For the 1W16C8B format, ho…
    in Inference with not image data Comment by Jack Huang July 2022

© Kneron, Inc.