Search results

  1. M

    Real-Time Video Super-Resolution Challenge

    We won't apply any post-processing on your output_tflite nor output_submit. We simply read your submit.png to numpy array and expect the value to be the same as your tflite output, which means the pixel value of your output_submit is in a range of 0-255, then the direct tflite output (the actual...
  2. M

    Real-Time Video Super-Resolution Challenge

    Instead of saving the tflite output to images(cv2.imwrite), we will load your provided result images and check the consistency directly on the tflite model output. It is expected that the returned submission status is failed because the reconstructed frames and README are not included. And you...
  3. M

    Real-Time Video Super-Resolution Challenge

    (1) The rule is applied in the test set (2) You should clamp the values in your tflite model.
  4. M

    Real-Time Video Super-Resolution Challenge

    Yes, that is correct.
  5. M

    Real-Time Video Super-Resolution Challenge

    (1) (2) To be marked as valid submission, your score should meet the following rule: - The hard constraint of PSNR and latency: PSNR [dB]: must be larger than 27dB; otherwise, the result would not be graded. Latency per frame [ms]: must be lower than 33ms; otherwise, the result would not be...
  6. M

    Real-Time Video Super-Resolution Challenge

    Please find the submission guideline at “Participate” and follow the instructions. You have a maximum of three submission in the test phase, and we will grade your last one. Thank you for the notice, we have fixed the typo. Q1. Yes, that is correct. Q2. You can specified all implementation for...
  7. M

    Real-Time Video Super-Resolution Challenge

    Yes, power is weighted for this challenge. As the real video SR use case is expected to be minutes+. This puts power consumption the first priority for the task. In this challenge, we try to set the PSNR/latency as the hard constraint for the task (minimum requirements for the user experience)...
  8. M

    Real-Time Video Super-Resolution Challenge

    Sorry for the previous mistake. We will grade your submissions based on the scoring policy for the final ranking of the competition. And to be eligible for prizes (not disqualified!), your total score should be higher than the baseline. That is, your total score should be higher than 71.399. The...
  9. M

    Real-Time Video Super-Resolution Challenge

    1. Sorry for the mistake. We will grade your submissions based on the scoring policy for the final ranking of the competition. And to be eligible for prizes (not disqualified!), your total score should be higher than the baseline. That is, your total score should be higher than 71.399. 2. Due...
  10. M

    Real-Time Video Super-Resolution Challenge

    Yes, that is correct.
  11. M

    Real-Time Video Super-Resolution Challenge

    1. There might be some measurement error in the automatic evaluation pipeline. We will manually measure all submissions in the final phase. 2. There are no restrictions to the data type and data range of your model. However, the input data range for inference is [0, 255]. You need to...
  12. M

    Real-Time Video Super-Resolution Challenge

    Please check your “readme.txt” in your submission and make sure you follow the submission guideline.
  13. M

    Real-Time Video Super-Resolution Challenge

    Thank you for the notice. We have fixed the calculation error on the webpage.
  14. M

    Real-Time Video Super-Resolution Challenge

    Your model is not fully quantized, therefore the model is inferenced on CPU. (Filter weight is int8 and bias weight is float32, that is not supported on our platform)
  15. M

    Real-Time Video Super-Resolution Challenge

    We had addressed some technical issues with the evaluation server, we will have a system update soon.
  16. M

    Real-Time Video Super-Resolution Challenge

    We had addressed some technical issues with the evaluation server, we will have a system update soon.
  17. M

    Real-Time Video Super-Resolution Challenge

    Dear organizers: Please provide your submission ID. The Optimization and Preference guideline can be found at “Particaipate”—> “Get Data”.
  18. M

    Real-Time Video Super-Resolution Challenge

    The energy consumption is currently measured in an automatic flow, therefore the result may vary under different device conditions. We will manually measure all submissions in the final phase for fair comparison.
  19. M

    Real-Time Video Super-Resolution Challenge

    We don’t restrict the energy consumption to be less than 1. However, there is a punishment according to the scoring policy specified in “Learn the Details” —> “Evaluation” if your energy consumption is larger than 1.
  20. M

    Real-Time Video Super-Resolution Challenge

    We are currently checking on your results_8_8.zip which is causing the unexpected behavior. In the meantime, please don't submit the result yet. Thank you.
  21. M

    Real-Time Video Super-Resolution Challenge

    Please check your Tensorflow version. (We suggest TF2.6) You can find more detail in your error log (stderr.txt).
  22. M

    Real-Time Video Super-Resolution Challenge

    Could you provide your submission ID?
  23. M

    Real-Time Video Super-Resolution Challenge

    You can follow the instruction here (https://github.com/MediaTek-NeuroPilot/tflite-neuron-delegate) to build our Neuron Delegate and evaluation on a Dimensity 9000 device.
  24. M

    Real-Time Video Super-Resolution Challenge

    Please follow the submission guideline specified in “Learn the Details”->”Evaluation”. Your zip archive should not include folders.
  25. M

    Real-Time Video Super-Resolution Challenge

    We are currently checking on your model. In the meantime, please don't submit any result yet. Thank you.
  26. M

    Real-Time Video Super-Resolution Challenge

    The runtime is measured on Mediatek Dimensity 9000 mobile device.
  27. M

    Real-Time Video Super-Resolution Challenge

    1. No, quantization is not necessary for your submission. All models will be rated under same criteria. 2. Yes, you can use extra data for training. 3. The final scoring formula will be released soon.
  28. M

    Real-Time Video Super-Resolution Challenge

    The runtime is measured with MediaTek Neuron delegate.
Top