Recent content by sayak

  1. sayak

    Real-Time Camera Scene Detection Challenge

    The submission instruction mail states the maximum number of entries have been increased to 10 but I still see it to be 3 -
  2. sayak

    Real-Time Camera Scene Detection Challenge

    Hi. Could someone clarify what is meant by test frames as mentioned in the last point of submission guidelines? > Download link(s) to the FULL results of ALL of the test frames Do test frames refer to the files we submit to the server that consist readme.txt, results.txt, and the TFLite model...
  3. sayak

    Learned Smartphone ISP Challenge

    Yes, that should be the case. Cc: @tulasi1729
  4. sayak

    AI Benchmark app not responding

    @Andrey Ignatov one final doubt regarding TFLite model for the challenge. If we fully integer quantize our models, then we should be good, right?
  5. sayak

    AI Benchmark app not responding

    Thank you. Appreciate your help.
  6. sayak

    Learned Smartphone ISP Challenge

    @Andrey Ignatov with this scaling, would this be affected as well (the final output of PyNet)? output_l0 = tf.nn.tanh(conv_l0_out) * 0.58 + 0.5
  7. sayak

    AI Benchmark app not responding

    I see. Got your point. I had initially misunderstood it. On a related note, I have been able to run full-integer quantized models on DSPs (an example). So, do you think that might be a case here?
  8. sayak

    AI Benchmark app not responding

    Got it. But didn't quite get "it is not supported by anyone" since TFLite Benchmark (v2) does support different quantizations including dynamic-range.
  9. sayak

    Learned Smartphone ISP Challenge

    Also, if you could shed a bit more light on the core math to scale the pixel values when dealing with different bits of images (e.g. for 10 bits it's 4*255, for 14 bits it's 16*255) that would be very helpful.
  10. sayak

    AI Benchmark app not responding

    Are you using Keras or TensorFlow for model conversion? - TensorFlow SavedModel What TensorFlow version did you use to convert the model? - TensorFlow 1.15.0 Is your model quantized or floating-point? - We used dynamic-range quantization. I am assuming we should not have used...
  11. sayak

    Learned Smartphone ISP Challenge

    I see. So, the baseline script could have been updated accordingly here. @Andrey Ignatov
  12. sayak

    Learned Smartphone ISP Challenge

    I serialized the output with integer data-type and kept the range to [0, 255]. Regarding your first question, this SO thread has some good explanations: https://stackoverflow.com/questions/58688633/how-to-convert-bayerrg8-format-image-to-rgb-image.
  13. sayak

    AI Benchmark app not responding

    I tried to benchmark our TFLite model (generated using a TF 1.15 runtime) using the AI Benchmark app. Here are additional details: * Device model id: RMX1801. * Android Version: 8.1. * When exactly this problem appears: After clicking "Run Model" under "Custom Model" tab.
  14. sayak

    Learned Smartphone ISP Challenge

    I tried to benchmark our model using the AI Benchmark app. After installing it on my phone (Realme Pro 2) it didn't open. Any clues?
  15. sayak

    Learned Smartphone ISP Challenge

    Alrighty. Thank you.
Top