Jump to content

marco@bigsis.tech

Members
  • Content Count

    14
  • Joined

  • Last visited

Everything posted by marco@bigsis.tech

  1. Hi All, I understand that in order to run an AI model on the NPU I have to convert it to RKNN, but whenever I do that my model (tf-lite) looses accuracy up to 15-20%. I have checked Rockchip_Trouble_Shooting_RKNN_Toolkit_V1.7.3_EN.pdf document in section 8.1 and it says that this issue might be related to setting mean_values/std_values incorrectly. then I found the below section in Rockchip_Trouble_Shooting_RKNN_Toolkit_V1.3.2_EN.pdf on how to set mean_values/std_values, but still don't quite understand it: I have 3 questions: 1) I am doing a binary classification and my Input data is (240,240,3) for training, would this be my (Cin0, Cin1,Cin2) ? 2) how do I set the Scale parameter ? 3)how do I get (Cout0,Cout1, Cout2) ? thank you, I would really appreciate your help
  2. Hi all, I have flashed the latest OS into the internal memory of the Tinker Edge R. I would please like to know how to clone the image file into other boards. thank you in advance
  3. Hi MThompson, I have tried to follow your suggestion. first, i have installed succesfully Tinker Edge R Debian V1.0.1 into the board. then whilst the board is connected to laptop via a USBC cable, i executed the command ''sudo reboot ums'' in the linux terminal on the tinker edge r. I can find the tinker edge r in the device manager but cannot find it in the balena etcher when selecting the target. Do you have any suggestion? thank you in advance
  4. Hi, I am having the same issue, did you manage to solve it?
  5. if i do ret = rknn.build(do_quantization=True, dataset='./dataset.txt', pre_compile=False) i get the below error but the model get built at the end. to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block2_add/add_113:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block2_add/add_114:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block3_1_conv/Conv2D_115:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block3_1_conv/Conv2D_116:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block3_2_conv/Conv2D_117:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block3_2_conv/Conv2D_118:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block3_3_conv/BiasAdd1_119:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block3_add/add_120:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv5_block3_add/add_121:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/avg_pool/Mean_122:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/dense/BiasAdd_123:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @StatefulPartitionedCall/0_124:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv2_block1_add/add_12_concat_126:out0 seems to be always 0, user might try to remove the correlative layer manually[0m [33mW tensor @sequential/resnet50/conv2_block1_add/add_12_conv_127:out0 seems to be always 0, user might try to remove the correlative layer manually[0m done --> Export RKNN model done
  6. Hi Tooz, Thank you very much for your response it was very helpful. I have converted the tf lite model to a rknn model and i had an improvement from 2 sec to 0.72 sec for inference. however is that the best that the tinker edge r can achieve? I didn't do the quantization in the rknn.build function, does it affect the speed in the inference? below is the code I used: rknn = RKNN() print('--> Loading model') ret = rknn.load_tflite(model = '/home/linaro/AI-big-data-1b.tflite') if ret != 0: print('Load failed!') exit(ret) print('done') # Build model print('--> Building model') ret = rknn.build(do_quantization=True) if ret != 0: print('Build *.rknn failed!') exit(ret) print('done') # Export rknn model print('--> Export RKNN model') ret = rknn.export_rknn("ai-module2.rknn") if ret != 0: print('Export *.rknn failed!') exit(ret) print('done')
  7. I have developed a CNN model for image classification with TensorFlow and then converted it to TensorFlow-lite. I have done a comparison between the inferencing time in the tinker edge and RPi 4B 4GB. It turned out that on the RPi 4 the inferencing time is faster ~ 1sec compared to the tinker edge r which is ~ 2sec. How is that possible. shouldn't the tinker edge have an AI accelerator unit? Am I missing something? I would please appreciate your help. thanks
  8. the camera module cable for this board is not as the rpi one, this one is smaller from one side. I would please like to know what is the camera cable type that comes with the tinker edge r and where I can buy a 3/5 meters cable of it.
  9. Hi, thank you again for your quick response. at the end I was able to solve the error by re-compiling opencv following the same tutorial BUT installing libgtk2.0-dev instead of libgtk-3-dev. I will try your suggestion as well. However I am currently facing another problem.. I am trying to capture videos from 4 usb cameras. I am able to preview only 3 cameras together, but if I try with 4 I gets the following error: (-215:Assertion failed) size.width>0 && size.height>0 in function 'cv::imshow Any suggestion please?
  10. thank you for your response, I will try uninstall opencv and recompile it with your modification and let you know as well
  11. Hi, thank you for your reply. No, I am building it on the Tinker Edge R, and the downloaded version of opencv after following that tutorial is 4.6.0. I also tried to execute the RKNN toolkit which gives opencv 4.4.0 and still got that error me
  12. Hi, thank you for your reply. No, I am building it on the Tinker Edge R, and the downloaded version of opencv after following that tutorial is 4.6.0. I also tried to execute the RKNN toolkit which gives opencv 4.4.0 and still got that error message.
  13. i have downloaded the debian 10 official realease from tinker board asus website and then followed your suggested tutorial to install opencv but i am still getting the error: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage'
×
×
  • Create New...