Recent content by deepernewbie

  1. D

    Real-Time Image Super-Resolution Challenge

    It means most of the challenges' preliminary results were published. Like "Compressed Image Single Image Superresolution" which I received the preliminary results. No news on this one yet. Either you rank 1st or the last if you have participated with a factsheet and required files. You will be...
  2. D

    Real-Time Image Super-Resolution Challenge

    Hi when should we expect the preliminary results? This is what the page states "03.23.2021 Preliminary test results release to the participants" Is it going to be later today or any change in the initial plans?
  3. D

    Real-Time Image Super-Resolution Challenge

    I have solved my problem, if you need some sort of linear mapping include it at the end of the model as a linear operator and as a floating point operator assuimg ranges 0-1 then use the tflite quantization it takes care of everything and calculates quantizations differently approximates the...
  4. D

    Real-Time Image Super-Resolution Challenge

    Yeah the same the feedback effects many things and only 3 days left and still no run results
  5. D

    Real-Time Image Super-Resolution Challenge

    you should do the scaling (scale zero point etc) and let tflite converter do its job for the quantization part. It should be like lr_image = cv2.imread(filename) #no extra code here sr_image = super_duper_model(lr_image) #here sr_image is 0-255 uint8 #no extra code here cv2.imshow(sr_image) #voila!
  6. D

    Real-Time Image Super-Resolution Challenge

    My understanding is raw_img = cv2.imread(imgName) is the input so anything below that should be integrated into the code especially these parts raw_img = raw_img / input_scale + input_zero_point and sr = (sr - output_zero_point) * output_scale so basically these are all "unfortunately"...
  7. D

    Real-Time Image Super-Resolution Challenge

    Thanks this was helpful!
  8. D

    Real-Time Image Super-Resolution Challenge

    dont use quantize model use quantize annotate layers for individual layers. the problem is first you use quantize annotate layers in upsample and the you try to quantize entire model so you already have a quantize annotated layer but quantize model tries to do annotation for all of the layers...
  9. D

    Real-Time Image Super-Resolution Challenge

    I am in the same shoes I hope some one can help
  10. D

    Real-Time Image Super-Resolution Challenge

    Even when I use Quatization Aware Training, when I convert from a model obtaining around 30dB it drops to 22-23dB's what am I doing wrong while quantizing can any body comment on this? Here is a minimal working example with the problem class KerasLite: def __init__(self,interpreter...
  11. D

    Real-Time Image Super-Resolution Challenge

    Should we fully quantize the model or can there be some layer unquantized for better accuracy?
  12. D

    Real-Time Image Super-Resolution Challenge

    Maybe there are parallel cores which can infer in parallel and the general inference is bounded by the resize branch? But thanks for sharing this
  13. D

    Real-Time Image Super-Resolution Challenge

    make sure your have model.tflite in Downloads folder it seems like it could not find the file
  14. D

    Real-Time Image Super-Resolution Challenge

    When are we going to get feedback for our recently sent models to the codalab server. It's been 1,5 days and still didn't get run result from the spreadsheet. This feedback is especially important since we dont have access to the hardware and not even know its architecture and drawbacks...
  15. D

    Real-Time Image Super-Resolution Challenge

    while using tflite in PC the model is not using the GPU and falling back to CPU since the tflite interpreter is not optimized for Nvidia GPUs but for mobile GPUs but still 779s is a lot. it seems like your model is kind of "huge" for the challenge, Try a very simple model convert it to tflite...
Top